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

    Neuronpedia

    INDEX
    Explanations

    python

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -mult
    -0.08
    不免
    -0.07
    等特点
    -0.07
    修养
    -0.07
     şüphe
    -0.06
    zm
    -0.06
    recall
    -0.06
    垡
    -0.06
    Clin
    -0.06
    难得
    -0.06
    POSITIVE LOGITS
    occo
    0.08
    isFunction
    0.07
    לס
    0.07
     maximum
    0.06
    ල
    0.06
     Permission
    0.06
     inne
    0.06
     Idle
    0.06
     У
    0.06
    .unlink
    0.06
    Act Density 0.276%

    No Known Activations