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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting that structures text into lists or instructions

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

    Imperative sentences or instructions

    np_acts-logits-general · gemini-2.0-flash

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.54
    UGE
    -0.49
     onBind
    -0.49
     Receives
    -0.46
     imposition
    -0.46
     gangen
    -0.45
     eaten
    -0.44
     Initial
    -0.44
    inent
    -0.44
     yardımcı
    -0.43
    POSITIVE LOGITS
     make
    0.83
     use
    0.81
     don
    0.80
    VersionUID
    0.74
     Make
    0.73
     put
    0.73
    ChildScrollView
    0.71
     JpaRepository
    0.69
     try
    0.69
     stick
    0.67
    Act Density 0.412%

    No Known Activations