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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    egis
    -0.07
     Helsinki
    -0.07
    Middleware
    -0.07
     Barang
    -0.06
    oriented
    -0.06
     Mall
    -0.06
     شکست
    -0.06
    写
    -0.06
     Gia
    -0.06
     pv
    -0.06
    POSITIVE LOGITS
    (pref
    0.07
     查看
    0.06
    зм
    0.06
     concerns
    0.06
     [(
    0.06
     tensorflow
    0.06
    [jj
    0.06
    (rate
    0.06
     şark
    0.06
    对于
    0.06
    Act Density 0.010%

    No Known Activations