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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _open
    -0.07
     모집
    -0.07
     نقشه
    -0.07
     मश
    -0.07
     Wid
    -0.07
    озем
    -0.06
     ZEND
    -0.06
    _
↵
↵
    -0.06
     sealing
    -0.06
     tarn
    -0.06
    POSITIVE LOGITS
     levels
    0.08
     Levels
    0.08
     level
    0.07
     органов
    0.07
     уровень
    0.06
    水平
    0.06
    ягом
    0.06
    Ahead
    0.06
     Podesta
    0.06
    .invoke
    0.06
    Act Density 0.037%

    No Known Activations