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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    奖金
    -0.08
    月下旬
    -0.07
     Suzanne
    -0.07
    <Animator
    -0.07
     Wagner
    -0.07
    先导
    -0.07
    难受
    -0.07
     עושים
    -0.07
    &e
    -0.07
     أمريكي
    -0.06
    POSITIVE LOGITS
    送往
    0.08
    .section
    0.08
    .Level
    0.08
     equalTo
    0.07
    ์
    0.07
    多达
    0.07
    诂
    0.07
    _MULT
    0.07
    (Properties
    0.07
    _Length
    0.07
    Act Density 0.056%

    No Known Activations