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

    Neuronpedia

    INDEX
    Explanations

    inclusive

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蜕变
    -0.07
    ær
    -0.07
    "People
    -0.07
    说不出
    -0.06
     Somebody
    -0.06
    _pf
    -0.06
    啶
    -0.06
    疲れ
    -0.06
     Hos
    -0.06
     محمد
    -0.06
    POSITIVE LOGITS
     offre
    0.08
    -metal
    0.07
    是没有
    0.07
    ㎖
    0.07
     aument
    0.07
    (Module
    0.07
     intact
    0.07
    Ư
    0.06
     uppercase
    0.06
    auge
    0.06
    Act Density 0.002%

    No Known Activations