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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    🍘
    -0.08
     luder
    -0.07
     المرأة
    -0.07
    תקש
    -0.06
    exc
    -0.06
    עמ
    -0.06
    חוסר
    -0.06
     davran
    -0.06
    ẻ
    -0.06
    /***************************************************************************↵
    -0.06
    POSITIVE LOGITS
     Tribunal
    0.07
    (font
    0.07
    (no
    0.07
     revolving
    0.07
    .model
    0.07
    -funded
    0.07
    _var
    0.07
     reaches
    0.07
    (Label
    0.06
    並將
    0.06
    Act Density 0.006%

    No Known Activations