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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dk
    -0.06
    พาะ
    -0.06
     відб
    -0.06
     lok
    -0.06
     вклад
    -0.06
     obed
    -0.06
     pork
    -0.06
     політи
    -0.06
     Colour
    -0.06
     khoảng
    -0.06
    POSITIVE LOGITS
    _ITER
    0.07
    Apr
    0.06
    --;↵↵
    0.06
    /net
    0.06
     '')↵↵
    0.06
    /board
    0.06
    季
    0.06
     JO
    0.06
    _rand
    0.06
    *C
    0.06
    Act Density 0.013%

    No Known Activations