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

    Neuronpedia

    INDEX
    Explanations

    discussions related to beliefs and evidence

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

    doubt or lack of certainty

    np_acts-logits-general · gemini-2.0-flash

    confidence and uncertainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    matchCondition
    -0.53
    Configurer
    -0.50
    gangs
    -0.50
     inflater
    -0.47
     становника
    -0.47
     sedentary
    -0.47
    ichio
    -0.46
     memperhatikan
    -0.46
    setupUi
    -0.45
    jacency
    -0.44
    POSITIVE LOGITS
     confidence
    1.07
     certainty
    0.99
    confidence
    0.93
     doubt
    0.93
     scepticism
    0.93
     faith
    0.91
     doubts
    0.90
     epistem
    0.90
     doubting
    0.89
     credibility
    0.88
    Act Density 1.026%

    No Known Activations