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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    置
    -0.07
     editors
    -0.07
    wen
    -0.07
    Davis
    -0.07
    cred
    -0.07
    VS
    -0.06
     Davis
    -0.06
     öğrenc
    -0.06
    Forward
    -0.06
    23
    -0.06
    POSITIVE LOGITS
     şans
    0.08
    ForeignKey
    0.06
     ResourceBundle
    0.06
     seasoned
    0.06
    osph
    0.06
    Нас
    0.06
     DisplayName
    0.06
    のも
    0.06
     dehydration
    0.06
    يمة
    0.06
    Act Density 0.055%

    No Known Activations