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

    Neuronpedia

    INDEX
    Explanations

    mourn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ')]↵
    -0.09
     magnesium
    -0.08
    信息系统
    -0.08
    "}↵
    -0.08
    ($('
    -0.08
    ')
↵
    -0.08
    _SUITE
    -0.07
    allax
    -0.07
    쫌
    -0.07
    "]↵
    -0.07
    POSITIVE LOGITS
    ǰ
    0.08
    ∇
    0.06
    ڧ
    0.06
    сут
    0.06
    𝚠
    0.06
    wa
    0.06
    创
    0.06
    义
    0.06
    береж
    0.06
    pl
    0.06
    Act Density 0.006%

    No Known Activations