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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating discussion or inquiry about various topics

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

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.53
     snippetHide
    -0.46
    twimg
    -0.44
     jspb
    -0.43
    writeFieldEnd
    -0.43
    tagHelperRunner
    -0.40
     otomatig
    -0.40
     ambigu
    -0.39
     HasFactory
    -0.39
     acacia
    -0.38
    POSITIVE LOGITS
    Norge
    0.42
    ISupport
    0.41
    zelfde
    0.40
    gorit
    0.40
    锈钢
    0.39
     affrontare
    0.39
    hoten
    0.39
     dealing
    0.39
    elemField
    0.38
    dealing
    0.38
    Act Density 0.103%

    No Known Activations