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

    Neuronpedia

    INDEX
    Explanations

    CR

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    b
    -0.09
    尽量
    -0.08
    繞
    -0.08
     soo
    -0.08
    툽
    -0.08
    eed
    -0.07
    lee
    -0.07
    )b
    -0.07
    eks
    -0.07
     farms
    -0.07
    POSITIVE LOGITS
    asticsearch
    0.07
    herence
    0.07
    Player
    0.07
     самостоя
    0.07
    ican
    0.07
    흐
    0.07
    픈
    0.07
    ほとんど
    0.06
    .IsFalse
    0.06
     كسارة
    0.06
    Act Density 0.008%

    No Known Activations