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

    Neuronpedia

    INDEX
    Explanations

    gain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discussions
    -0.08
    _g
    -0.07
     drag
    -0.07
     es
    -0.07
     действия
    -0.07
     "\
    -0.07
    還
    -0.07
     mode
    -0.06
     курс
    -0.06
     counterparts
    -0.06
    POSITIVE LOGITS
    czę
    0.07
    冔
    0.07
    _requests
    0.07
    וסף
    0.07
    تحض
    0.07
    莫斯
    0.07
    ↗
    0.07
     thirst
    0.07
    ✄
    0.07
    秆
    0.07
    Act Density 0.005%

    No Known Activations