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

    Neuronpedia

    INDEX
    Explanations

    named

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еча
    -0.07
    sąd
    -0.07
    뺴
    -0.06
    足球
    -0.06
    —all
    -0.06
     función
    -0.06
    wf
    -0.06
     lp
    -0.06
     defence
    -0.06
     ass
    -0.06
    POSITIVE LOGITS
    あと
    0.07
    ﯘ
    0.07
    .stage
    0.07
    _pair
    0.07
    .Factory
    0.07
    ARK
    0.07
    骜
    0.07
     Datagram
    0.07
     Sith
    0.07
    AAD
    0.07
    Act Density 0.001%

    No Known Activations