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

    Neuronpedia

    INDEX
    Explanations

    programming and software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     palms
    -0.07
     urinary
    -0.06
    ToEnd
    -0.06
     undercut
    -0.06
    yard
    -0.06
     LIFE
    -0.06
    CE
    -0.06
     pursue
    -0.06
     Bolshevik
    -0.06
    _languages
    -0.06
    POSITIVE LOGITS
    authorized
    0.07
    (alpha
    0.07
    977
    0.07
     下跌
    0.06
     Autor
    0.06
    Ệ
    0.06
    ossed
    0.06
    immutable
    0.06
     relieve
    0.06
    卒
    0.06
    Act Density 0.008%

    No Known Activations