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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    template
    -0.07
    _cmd
    -0.07
    特別
    -0.07
    Hand
    -0.07
     Outstanding
    -0.07
     khoản
    -0.07
     shared
    -0.07
     tread
    -0.06
    tee
    -0.06
    نين
    -0.06
    POSITIVE LOGITS
    .Since
    0.08
    共和
    0.08
    🇷
    0.07
    阆
    0.07
     probability
    0.07
    龙门
    0.07
    休闲
    0.07
    [o
    0.07
     Diversity
    0.07
     açıs
    0.07
    Act Density 0.001%

    No Known Activations