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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reading
    -0.07
     Cartoon
    -0.07
    cheon
    -0.07
     following
    -0.07
    命中
    -0.07
    (hidden
    -0.07
    hexdigest
    -0.06
    .walk
    -0.06
     Christ
    -0.06
    otten
    -0.06
    POSITIVE LOGITS
    iasm
    0.08
     الاسلام
    0.07
    .styles
    0.07
     elo
    0.07
    >*
    0.07
    faq
    0.07
    >r
    0.07
     lah
    0.07
     успех
    0.07
    empor
    0.07
    Act Density 0.002%

    No Known Activations