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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    プログラム
    -0.08
    istas
    -0.07
    Map
    -0.07
     Platform
    -0.07
    _code
    -0.07
     ski
    -0.07
     site
    -0.07
     strategy
    -0.06
     recipe
    -0.06
    משחק
    -0.06
    POSITIVE LOGITS
    -initialized
    0.07
    .ReadAll
    0.07
    enzhen
    0.07
     ATA
    0.07
    阏
    0.07
     такие
    0.06
     Ô
    0.06
     supp
    0.06
    .reason
    0.06
     olması
    0.06
    Act Density 0.011%

    No Known Activations