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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ipo
    -0.07
     Dealer
    -0.07
    inho
    -0.07
    .listdir
    -0.06
     dét
    -0.06
     Ansi
    -0.06
    érer
    -0.06
     إدارة
    -0.06
     appellate
    -0.06
     palavra
    -0.06
    POSITIVE LOGITS
    .be
    0.07
     shoe
    0.07
    Uvs
    0.07
     Боль
    0.06
    是最
    0.06
    插
    0.06
    的那个
    0.06
    =a
    0.06
    _rot
    0.06
     참
    0.06
    Act Density 0.663%

    No Known Activations