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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .operator
    -0.08
    ماری
    -0.07
    (drop
    -0.07
    より
    -0.07
    ='"
    -0.07
    .convert
    -0.07
    陆
    -0.07
     міста
    -0.07
     서비스
    -0.06
     fro
    -0.06
    POSITIVE LOGITS
     Psychiat
    0.06
    ,path
    0.06
     Ankara
    0.06
    ......↵↵
    0.06
    _deck
    0.06
    _OPEN
    0.06
     mitig
    0.06
    breaking
    0.06
    .''↵↵
    0.06
    uttgart
    0.06
    Act Density 0.363%

    No Known Activations