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

    Neuronpedia

    INDEX
    Explanations

    Gattaca, Altered Carbon, Neuromancer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    1.09
    in
    0.95
    在
    0.93
    ও
    0.91
    s
    0.89
    ’
    0.88
    ado
    0.88
    ines
    0.86
    ins
    0.84
    ina
    0.83
    POSITIVE LOGITS
     вас
    1.02
     вам
    0.85
     молит
    0.75
     вет
    0.74
    Также
    0.74
     жерт
    0.73
     тебе
    0.71
     ваш
    0.71
     vaše
    0.70
    feb
    0.70
    Act Density 0.000%

    No Known Activations