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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms indicating evaluation or assessment

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

    drawn from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addContainerGap
    -0.59
    tagHelperRunner
    -0.55
     zijne
    -0.44
     pinulongan
    -0.42
     auffi
    -0.39
    عرِّف
    -0.39
     banques
    -0.38
     dieß
    -0.38
     صوتيه
    -0.38
    sizeCache
    -0.37
    POSITIVE LOGITS
     noDo
    0.46
    postIndex
    0.45
    //
    0.45
    憾
    0.44
    Externí
    0.42
    Kudos
    0.41
     raincoat
    0.41
    امی
    0.40
    avía
    0.40
    Życiorys
    0.40
    Act Density 0.685%

    No Known Activations