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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    -1.06
     '
    -0.95
     realizada
    -0.90
     U
    -0.90
     its
    -0.88
     how
    -0.86
     aunque
    -0.86
    ディダス
    -0.85
     than
    -0.85
     aseguró
    -0.85
    POSITIVE LOGITS
     bluse
    1.01
    atering
    1.00
     Secondo
    0.99
    timmen
    0.98
     الصف
    0.96
     memen
    0.96
     рестайлинг
    0.95
     cei
    0.95
     guste
    0.94
    ด์
    0.94
    Act Density 0.048%

    No Known Activations