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

    Neuronpedia

    INDEX
    Explanations

    Python classes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    滋润
    -0.07
     Tyson
    -0.06
     وسلم
    -0.06
     Financing
    -0.06
     refreshing
    -0.06
    冲锋
    -0.06
     freopen
    -0.06
     glow
    -0.06
     ila
    -0.06
    坩
    -0.06
    POSITIVE LOGITS
    iptables
    0.07
    ?}",
    0.07
     tanks
    0.07
    ﺒ
    0.06
    KV
    0.06
    bh
    0.06
    _DAYS
    0.06
     nets
    0.06
    ubbles
    0.06
    erver
    0.06
    Act Density 0.003%

    No Known Activations