Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    assertions and claims of truthfulness or fact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    truthfulness and factuality

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects emphatic assertions that something is true or real—claims by the speaker insisting the information is genuine or not a joke.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     conmigo
    -0.52
     romántico
    -0.49
     cuáles
    -0.46
    warted
    -0.46
     turístico
    -0.45
     diría
    -0.44
    戬
    -0.44
     muñecas
    -0.44
     pareja
    -0.44
     unknownFields
    -0.44
    POSITIVE LOGITS
    /**
    0.49
    GIVEREF
    0.48
    //
    0.37
    mybatisplus
    0.35
     exist
    0.35
    evidence
    0.34
    실
    0.34
     MutableLiveData
    0.33
     Exist
    0.33
    Confirmed
    0.32
    Act Density 0.045%

    No Known Activations