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
     spolu
    -0.07
    Home
    -0.07
    .visualization
    -0.07
    ěti
    -0.07
    folios
    -0.06
     (('
    -0.06
    اویر
    -0.06
    udad
    -0.06
    ような
    -0.06
     Welt
    -0.06
    POSITIVE LOGITS
    ()
    0.08
    803
    0.06
    هد
    0.06
    一直
    0.06
    _paragraph
    0.06
     transactions
    0.06
    942
    0.06
    902
    0.06
    ینگ
    0.06
    IOS
    0.06
    Act Density 0.002%

    No Known Activations