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

    Neuronpedia

    INDEX
    Explanations

    Japanese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ty
    -0.06
    TypeID
    -0.06
     чаще
    -0.06
    Aaron
    -0.06
     ل
    -0.06
     сто
    -0.06
     unfolded
    -0.06
    فضل
    -0.06
    ERTICAL
    -0.06
    .uni
    -0.06
    POSITIVE LOGITS
     FIX
    0.08
    ('.')[
    0.07
    acao
    0.07
    etically
    0.06
     treat
    0.06
     Лі
    0.06
    quite
    0.06
    евых
    0.06
    etí
    0.06
     míst
    0.06
    Act Density 0.038%

    No Known Activations