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

    Neuronpedia

    INDEX
    Explanations

    Business and technology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    クロ
    -0.08
    虱
    -0.07
    within
    -0.07
     При
    -0.07
    Given
    -0.06
    铥
    -0.06
    cola
    -0.06
    同一
    -0.06
    Ӣ
    -0.06
    某一
    -0.06
    POSITIVE LOGITS
    热血
    0.08
     entrenched
    0.07
     START
    0.07
    buttons
    0.07
    忐
    0.07
    借贷
    0.07
    原著
    0.06
    最好不要
    0.06
     Kenneth
    0.06
    鳊
    0.06
    Act Density 0.106%

    No Known Activations