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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    animation
    -0.07
    郭
    -0.07
    deal
    -0.07
    ‌گ
    -0.06
     poems
    -0.06
     greatest
    -0.06
    pite
    -0.06
    Lang
    -0.06
    rray
    -0.06
    机关
    -0.06
    POSITIVE LOGITS
     invol
    0.07
    ($_
    0.07
    .validation
    0.07
     %+
    0.07
     oauth
    0.06
     Wyoming
    0.06
    $",
    0.06
    ->{_
    0.06
     Pornhub
    0.06
    .pojo
    0.06
    Act Density 0.004%

    No Known Activations