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

    Neuronpedia

    INDEX
    Explanations

    code and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    茛
    -0.07
    مقا
    -0.07
    .Dispatch
    -0.07
    时时
    -0.07
    鹆
    -0.06
     finde
    -0.06
     utilisateur
    -0.06
    郤
    -0.06
     ventana
    -0.06
     monumental
    -0.06
    POSITIVE LOGITS
    _NONNULL
    0.07
    BN
    0.07
    뿐
    0.07
     Sao
    0.06
    .mkdir
    0.06
    ער
    0.06
    另外
    0.06
     OH
    0.06
     attackers
    0.06
    -UA
    0.06
    Act Density 0.001%

    No Known Activations