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

    Neuronpedia

    INDEX
    Explanations

    int

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    окрем
    -0.07
    joy
    -0.07
    _ONE
    -0.07
     encrypt
    -0.07
     Key
    -0.06
    Flip
    -0.06
     мон
    -0.06
    Component
    -0.06
    _tra
    -0.06
     key
    -0.06
    POSITIVE LOGITS
    عان
    0.07
    urger
    0.06
    _regeneration
    0.06
    ่เป
    0.06
     возможность
    0.06
     olduğuna
    0.06
     ώρα
    0.06
    里的
    0.06
    Sync
    0.06
     بـ
    0.06
    Act Density 0.026%

    No Known Activations