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

    Neuronpedia

    INDEX
    Explanations

    cement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     유지
    -0.07
    าชน
    -0.06
    ────
    -0.06
    ニュ
    -0.06
     citizen
    -0.06
     včetně
    -0.06
    icides
    -0.06
    _UNICODE
    -0.06
     надо
    -0.06
     يك
    -0.06
    POSITIVE LOGITS
    .mock
    0.07
    .volley
    0.06
     Artist
    0.06
     foss
    0.06
    _expire
    0.06
    (cont
    0.06
    -wsj
    0.06
     Singleton
    0.06
    老
    0.06
     obj
    0.06
    Act Density 0.014%

    No Known Activations