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

    Neuronpedia

    INDEX
    Explanations

    once

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mah
    -0.07
    หลด
    -0.07
     Jae
    -0.07
     แ
    -0.06
     Hobby
    -0.06
     numRows
    -0.06
    _PRESENT
    -0.06
    -band
    -0.06
    -La
    -0.06
     nostra
    -0.06
    POSITIVE LOGITS
    /git
    0.07
    idental
    0.06
     Approximately
    0.06
    .contents
    0.06
    _MISS
    0.06
    居民
    0.06
    大家
    0.06
     Cumhurbaşkanı
    0.06
    NAME
    0.06
     cognition
    0.06
    Act Density 0.017%

    No Known Activations