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

    Neuronpedia

    INDEX
    Explanations

    email queues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INSTALL
    -0.07
    '));
    -0.06
     Frid
    -0.06
    mis
    -0.06
     Catal
    -0.06
     Reid
    -0.06
    surface
    -0.06
    DIG
    -0.06
    불
    -0.06
    iy
    -0.06
    POSITIVE LOGITS
    овари
    0.07
    跡
    0.07
     Zahl
    0.07
    .drawLine
    0.06
     آزم
    0.06
    .JTable
    0.06
     EDUC
    0.06
    _staff
    0.06
     Thankfully
    0.06
     dop
    0.06
    Act Density 0.321%

    No Known Activations