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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spar
    -0.07
    cae
    -0.06
    Nos
    -0.06
    Mil
    -0.06
     Semaphore
    -0.06
     接
    -0.06
    Bet
    -0.06
    .Roles
    -0.06
    _received
    -0.06
     лучше
    -0.06
    POSITIVE LOGITS
     अ
    0.07
     więc
    0.07
     ω
    0.07
    러운
    0.07
     Savaş
    0.06
    IFICATION
    0.06
     autism
    0.06
     kırmızı
    0.06
     axiom
    0.06
    .addHandler
    0.06
    Act Density 0.016%

    No Known Activations