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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and parentheses in the text

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

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.44
    aarrggbb
    -0.37
    WireFormatLite
    -0.35
     AssemblyTitle
    -0.34
     Drill
    -0.33
     gols
    -0.32
     drill
    -0.32
    المكان
    -0.32
    ---*/
    -0.31
    ruhe
    -0.30
    POSITIVE LOGITS
    styleType
    0.54
     виправивши
    0.51
    ConstraintMaker
    0.48
     Aoki
    0.47
    覬
    0.46
    पया
    0.46
    ystick
    0.45
    脚注の使い方
    0.45
     hui
    0.45
    unsplash
    0.44
    Act Density 0.117%

    No Known Activations