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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section

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

    Text following a colon or quotation mark

    np_acts-logits-general · gemini-2.0-flash

    special codes like [@B

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ModelAdmin
    -0.67
     nakalista
    -0.55
    wpi
    -0.54
    -0.54
     Архивировано
    -0.53
    ungkin
    -0.52
     отмети
    -0.51
    -0.50
    moment
    -0.50
    MessageOf
    -0.50
    POSITIVE LOGITS
     الدولى
    0.60
    SequentialGroup
    0.59
     covid
    0.58
     NSCoder
    0.57
    Covid
    0.55
     otomatig
    0.55
     COVID
    0.55
     Covid
    0.53
    wapV
    0.53
    AutoScaleMode
    0.53
    Act Density 0.040%

    No Known Activations