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

    Neuronpedia

    INDEX
    Explanations

    date: `dated`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ación
    1.23
    ב
    1.13
    ب
    1.02
    ]}.
    0.98
    $，
    0.97
     enfri
    0.97
    ک
    0.96
    ,$$
    0.96
    هم
    0.94
    偻
    0.93
    POSITIVE LOGITS
    ди
    1.18
    ки
    1.17
    ни
    1.09
    ду
    1.07
     moisturizing
    1.06
    ка
    1.03
    ö
    1.01
     к
    0.99
    ει
    0.98
    '}}
    0.96
    Act Density 0.001%

    No Known Activations