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

    Neuronpedia

    INDEX
    Explanations

    Amounts owed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    payload
    -0.07
    EDIT
    -0.07
    НІ
    -0.06
    _VF
    -0.06
    PROTO
    -0.06
     Examples
    -0.06
    IRC
    -0.06
    oupon
    -0.06
     Haw
    -0.06
    ाओ
    -0.06
    POSITIVE LOGITS
     gost
    0.06
    .awt
    0.06
     subgroup
    0.06
     leurs
    0.06
     geniş
    0.06
     hấp
    0.06
     сч
    0.06
    접
    0.06
     çalışmaları
    0.06
     crimson
    0.06
    Act Density 0.022%

    No Known Activations