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

    Neuronpedia

    INDEX
    Explanations

    common English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    출장
    -0.07
     Bulk
    -0.07
    .Project
    -0.06
    (pkt
    -0.06
     Faul
    -0.06
     activated
    -0.06
     roadside
    -0.06
     DEFAULT
    -0.06
     roli
    -0.06
     Utils
    -0.06
    POSITIVE LOGITS
    plx
    0.07
    AILY
    0.06
    revision
    0.06
    Initial
    0.06
     Address
    0.06
    advisor
    0.06
     archivos
    0.06
     Excel
    0.06
    _atts
    0.06
    _GREEN
    0.06
    Act Density 0.001%

    No Known Activations