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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Refer
    -0.07
    023
    -0.06
    (preg
    -0.06
     pleasing
    -0.06
    들에게
    -0.06
    784
    -0.06
     rho
    -0.06
     лише
    -0.06
    _integer
    -0.06
    Flying
    -0.06
    POSITIVE LOGITS
     mientras
    0.08
    ávání
    0.07
     predecess
    0.06
     مسلمان
    0.06
     имени
    0.06
     Britain
    0.06
    reation
    0.06
     yarat
    0.06
    Indices
    0.06
     MEN
    0.06
    Act Density 0.101%

    No Known Activations