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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .remaining
    -0.07
    estring
    -0.07
    _kb
    -0.06
    BSD
    -0.06
    Spider
    -0.06
     Asc
    -0.06
     Hawk
    -0.06
    XXX
    -0.06
    (ERR
    -0.06
    Future
    -0.06
    POSITIVE LOGITS
    奴
    0.06
    �
    0.06
    ịp
    0.06
    ubectl
    0.06
    enheim
    0.06
     नह
    0.06
    0.06
     prů
    0.06
    یلی
    0.06
     doma
    0.06
    Act Density 0.004%

    No Known Activations