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

    Neuronpedia

    INDEX
    Explanations

    );

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sob
    -0.07
    oltip
    -0.07
     Glas
    -0.07
     tặng
    -0.06
     využí
    -0.06
     filme
    -0.06
    ために
    -0.06
     embod
    -0.06
     intervals
    -0.06
    GL
    -0.06
    POSITIVE LOGITS
    kills
    0.06
    update
    0.06
    -blind
    0.06
    ザー
    0.06
    Resolved
    0.06
    _update
    0.06
    ogens
    0.06
    previous
    0.06
    _reset
    0.06
     віднов
    0.06
    Act Density 0.000%

    No Known Activations