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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sexe
    -0.07
     dél
    -0.07
    叶
    -0.07
     pow
    -0.06
     ση
    -0.06
    _su
    -0.06
     charitable
    -0.06
     frying
    -0.06
    .creator
    -0.06
    éné
    -0.06
    POSITIVE LOGITS
    閉
    0.06
     Amerika
    0.06
    ^^
    0.06
     어
    0.06
    (vector
    0.06
    には
    0.06
    opyright
    0.06
    entic
    0.06
    캐
    0.06
    できます
    0.06
    Act Density 0.000%

    No Known Activations