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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hızlı
    -0.08
     물론
    -0.08
     верш
    -0.08
     beste
    -0.07
     alleviate
    -0.07
     kaum
    -0.07
     гора
    -0.07
     αποτε
    -0.07
    .pipeline
    -0.07
     দ্রুত
    -0.07
    POSITIVE LOGITS
     duration
    0.17
    Duration
    0.16
     Duration
    0.16
    (duration
    0.15
     durée
    0.15
    _duration
    0.15
     동안
    0.14
    동안
    0.14
     duração
    0.14
     duración
    0.14
    Act Density 0.047%

    No Known Activations