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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     отношения
    -0.07
    -du
    -0.06
    írk
    -0.06
    (o
    -0.06
    Dirty
    -0.06
     residuals
    -0.06
     수정
    -0.06
    .norm
    -0.06
     Roc
    -0.06
    тися
    -0.06
    POSITIVE LOGITS
    ादन
    0.07
    ラー
    0.07
     compassionate
    0.06
     Ils
    0.06
    许多
    0.06
     NotFound
    0.06
    Якщо
    0.06
     toto
    0.06
    incorrect
    0.06
     Cyril
    0.06
    Act Density 0.015%

    No Known Activations