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

    Neuronpedia

    INDEX
    Explanations

    code filenames

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Anyway
    -0.07
    /test
    -0.07
     Hav
    -0.06
     Hol
    -0.06
    _unicode
    -0.06
    -star
    -0.06
     Dale
    -0.06
     LaTeX
    -0.06
    qed
    -0.06
    丈夫
    -0.06
    POSITIVE LOGITS
    (Op
    0.07
     visited
    0.07
    HY
    0.06
     Pf
    0.06
    <dyn
    0.06
     П
    0.06
    gorm
    0.06
    怕
    0.06
    ιβ
    0.06
    rength
    0.06
    Act Density 0.014%

    No Known Activations