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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Organization
    -0.07
     peu
    -0.07
    -0.07
     губ
    -0.06
    字
    -0.06
    阶
    -0.06
    Std
    -0.06
     thirsty
    -0.06
    )o
    -0.06
     Erect
    -0.06
    POSITIVE LOGITS
     branded
    0.07
    лат
    0.06
    plied
    0.06
    advance
    0.06
    UpperCase
    0.06
    -xl
    0.06
    ーカー
    0.06
     moduleName
    0.06
    ENCY
    0.06
    _lens
    0.06
    Act Density 0.000%

    No Known Activations