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

    Neuronpedia

    INDEX
    Explanations

    social

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🏮
    -0.07
    IFI
    -0.07
    /out
    -0.07
     delve
    -0.07
    )?.
    -0.07
    .listen
    -0.07
    🎧
    -0.07
    釐
    -0.06
     TSR
    -0.06
    }));↵
    -0.06
    POSITIVE LOGITS
    단체
    0.08
     SolidColorBrush
    0.07
     Climate
    0.07
    _quantity
    0.07
    Drawable
    0.07
    猬
    0.06
    _contact
    0.06
    人死亡
    0.06
     Marie
    0.06
     Social
    0.06
    Act Density 0.025%

    No Known Activations