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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aucun
    -0.10
     Aucun
    -0.08
    olis
    -0.08
     geen
    -0.08
     الاح
    -0.07
     sigma
    -0.07
     sól
    -0.07
     None
    -0.07
     incorporates
    -0.07
     imprime
    -0.07
    POSITIVE LOGITS
    र्थ
    0.08
     ए
    0.08
     readline
    0.08
     length
    0.08
     randomized
    0.08
    .Length
    0.07
    ergency
    0.07
     perfor
    0.07
     выбран
    0.07
    (length
    0.07
    Act Density 0.003%

    No Known Activations