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

    Neuronpedia

    INDEX
    Explanations

    prohibits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    namento
    0.47
     บาท
    0.43
    赠
    0.42
    🎇
    0.42
     therapeutics
    0.41
     Therapeutics
    0.40
     smiled
    0.40
    रायपुर
    0.40
    dai
    0.40
     Metallurgy
    0.39
    POSITIVE LOGITS
    ска
    0.43
    ћи
    0.43
    ת
    0.42
    га
    0.42
    গের
    0.42
    ше
    0.41
    수를
    0.41
    точка
    0.41
    ть
    0.40
    вый
    0.40
    Act Density 17.596%

    No Known Activations