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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çıkış
    -0.07
     神
    -0.07
     beers
    -0.07
    ’ı
    -0.07
     adultes
    -0.06
    .setInput
    -0.06
     grands
    -0.06
     Scotland
    -0.06
     xpos
    -0.06
    osomal
    -0.06
    POSITIVE LOGITS
    riott
    0.06
    leme
    0.06
    _action
    0.06
    Book
    0.06
     juego
    0.06
    ию
    0.06
    Electronic
    0.06
     depleted
    0.06
    دهم
    0.06
     book
    0.06
    Act Density 0.016%

    No Known Activations