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

    Neuronpedia

    INDEX
    Explanations

    categories, classifications, or numeric representations related to data and measurements

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

    before question marks, commas, or semicolons

    np_acts-logits-general · gemini-2.0-flash

    defining or naming categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jefus
    -0.77
     againſt
    -0.77
     Majefty
    -0.75
     étoit
    -0.74
     themſelves
    -0.73
     picioare
    -0.73
     Efq
    -0.73
     myſelf
    -0.73
     Shakspeare
    -0.72
     caufe
    -0.72
    POSITIVE LOGITS
     social
    0.70
     typelib
    0.69
     physical
    0.67
     Social
    0.61
    onViewCreated
    0.61
     onBind
    0.59
     safety
    0.58
     environmental
    0.57
     organizational
    0.57
     internal
    0.57
    Act Density 1.605%

    No Known Activations