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

    Neuronpedia

    INDEX
    Explanations

    H

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Router
    -0.07
    іїв
    -0.07
    kker
    -0.06
    kovi
    -0.06
    static
    -0.06
    ्रमण
    -0.06
    欧美
    -0.06
    485
    -0.06
     disponible
    -0.06
    shouldBe
    -0.06
    POSITIVE LOGITS
    &s
    0.06
    补
    0.06
     Volkswagen
    0.06
     tous
    0.06
     ενώ
    0.06
     nailed
    0.06
     whirl
    0.06
    <C
    0.06
    (sorted
    0.06
    .DataBindings
    0.06
    Act Density 0.000%

    No Known Activations