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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing personal reflections or thoughts

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

    "thought" or thinking

    np_acts-logits-general · gemini-2.0-flash

    thought for sure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.59
    styleUrls
    -0.51
    Datuak
    -0.50
    MarshalTo
    -0.50
    SharedDtor
    -0.49
     kasarigan
    -0.47
    Autoritní
    -0.47
     насељу
    -0.45
    PerformLayout
    -0.45
     sessionFactory
    -0.44
    POSITIVE LOGITS
     might
    0.50
     thought
    0.46
    might
    0.44
     Thought
    0.41
    Thought
    0.41
     maybe
    0.39
    thought
    0.38
    Jîn
    0.38
     Maybe
    0.37
    以為
    0.37
    Act Density 0.173%

    No Known Activations