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

    Neuronpedia

    INDEX
    Explanations

    say "Billboard"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rupture
    -0.07
    percentage
    -0.07
    _sup
    -0.07
    _ce
    -0.07
     tx
    -0.07
    оки
    -0.06
    ulant
    -0.06
    ками
    -0.06
     tern
    -0.06
    为什么
    -0.06
    POSITIVE LOGITS
     corrobor
    0.07
     обще
    0.06
    .GPIO
    0.06
    ahrung
    0.06
    <Entry
    0.06
    Reality
    0.06
    .gms
    0.06
    จะได
    0.06
    (SP
    0.06
    iaz
    0.06
    Act Density 0.009%

    No Known Activations