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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (percent
    -0.07
    Equ
    -0.07
    Numbers
    -0.07
    ẩ
    -0.07
     reach
    -0.07
    (ii
    -0.07
     grat
    -0.07
     Kings
    -0.07
    驱
    -0.06
    %s
    -0.06
    POSITIVE LOGITS
     HIP
    0.07
    Ḫ
    0.06
    _USED
    0.06
    .setStyleSheet
    0.06
    另一位
    0.06
     Dow
    0.06
    <header
    0.06
    Bootstrap
    0.06
    铏
    0.06
    Cookie
    0.06
    Act Density 0.081%

    No Known Activations