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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating capacity or space for improvement

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

    room for improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Thursday
    -0.39
     military
    -0.36
     result
    -0.35
     resultList
    -0.35
    ACIONAL
    -0.34
     Defensa
    -0.34
     the
    -0.33
     principal
    -0.33
    écution
    -0.33
     its
    -0.32
    POSITIVE LOGITS
    DockStyle
    0.84
    AnchorStyles
    0.84
    ChildScrollView
    0.82
    tagHelperRunner
    0.73
    itespace
    0.73
    rungsseite
    0.69
    setVerticalGroup
    0.69
     nahilalakip
    0.69
     arşivlendi
    0.67
    eway
    0.65
    Act Density 0.008%

    No Known Activations