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

    Neuronpedia

    INDEX
    Explanations

    copy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FullYear
    -0.07
    أهمية
    -0.07
    .docs
    -0.07
    \AppData
    -0.07
    Cómo
    -0.07
    _ylim
    -0.07
    Tên
    -0.07
     toc
    -0.06
    encion
    -0.06
    _tool
    -0.06
    POSITIVE LOGITS
     (`
    0.07
     democrat
    0.07
    מרת
    0.07
    五
    0.06
     United
    0.06
    国有
    0.06
     community
    0.06
    קוב
    0.06
     ограни
    0.06
     councillors
    0.06
    Act Density 0.001%

    No Known Activations