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

    Neuronpedia

    INDEX
    Explanations

    reading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .jpg
    -0.08
    胡
    -0.08
    ể
    -0.07
    &o
    -0.07
     Applicants
    -0.07
     specific
    -0.07
    ensi
    -0.07
     diluted
    -0.07
     nên
    -0.07
    밑
    -0.07
    POSITIVE LOGITS
    最初的
    0.07
     projectiles
    0.07
     spir
    0.07
    command
    0.07
    (numbers
    0.07
    もら
    0.07
    前行
    0.06
    vard
    0.06
     Rubin
    0.06
    (actions
    0.06
    Act Density 0.001%

    No Known Activations