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

    Neuronpedia

    INDEX
    Explanations

    binary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مثل
    -0.08
    _pkt
    -0.07
    oku
    -0.07
    ouch
    -0.07
     Sara
    -0.07
     Mexican
    -0.07
    .utils
    -0.07
    amba
    -0.07
    linear
    -0.07
     basketball
    -0.07
    POSITIVE LOGITS
    ѷ
    0.08
     properties
    0.07
    薁
    0.07
    yalty
    0.07
    ㌽
    0.07
     therefore
    0.07
    抗体
    0.07
     rağ
    0.07
    perse
    0.06
    yclic
    0.06
    Act Density 0.006%

    No Known Activations