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

    Neuronpedia

    INDEX
    Explanations

    smiled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Svens
    -0.07
     Mirror
    -0.07
     Explore
    -0.07
     moves
    -0.07
     Kron
    -0.07
     Alias
    -0.07
     lbs
    -0.06
     PROM
    -0.06
     پرو
    -0.06
     Flying
    -0.06
    POSITIVE LOGITS
     ocup
    0.07
    aus
    0.07
    Dies
    0.06
    .interfaces
    0.06
    vál
    0.06
     enfants
    0.06
    ُن
    0.06
    (fd
    0.06
    +b
    0.06
    افع
    0.06
    Act Density 0.013%

    No Known Activations