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

    Neuronpedia

    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     modeled
    -0.07
     rewriting
    -0.07
    qw
    -0.06
     pari
    -0.06
     spouses
    -0.06
     Lamar
    -0.06
     plateau
    -0.06
    Seek
    -0.06
    Recent
    -0.06
    (({
    -0.06
    POSITIVE LOGITS
    _STRING
    0.08
    ельно
    0.07
    負
    0.07
     Ř
    0.06
     Darth
    0.06
    ruptcy
    0.06
    ادگی
    0.06
    ActivityIndicatorView
    0.06
     надеж
    0.06
    �乐
    0.06
    Act Density 0.000%

    No Known Activations