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

    Neuronpedia

    INDEX
    Explanations

    and, comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abused
    -0.07
    ывает
    -0.07
     Minute
    -0.07
     Build
    -0.06
     misdemeanor
    -0.06
     organiz
    -0.06
    ustil
    -0.06
     might
    -0.06
    ebilirsiniz
    -0.06
     aval
    -0.06
    POSITIVE LOGITS
     giorn
    0.07
    ่านมา
    0.07
     blí
    0.06
    GC
    0.06
     Bounty
    0.06
    (crate
    0.06
    .erb
    0.06
    daş
    0.06
    _NAMESPACE
    0.06
    jpg
    0.06
    Act Density 0.092%

    No Known Activations