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

    Neuronpedia

    INDEX
    Explanations

    characteristics, behaviors, phenomena, or reactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਤੇ
    0.51
    音声
    0.47
     मोठ
    0.43
    價格
    0.43
    ᓵ
    0.41
    价格
    0.40
    ת
    0.40
    刮
    0.39
    ുകൊണ്ടാണ്
    0.39
    送信
    0.38
    POSITIVE LOGITS
     Characteristics
    0.59
     Plugin
    0.52
     Phenomena
    0.51
     reactions
    0.48
     Distinguished
    0.48
     karakteristik
    0.48
     behaviors
    0.48
     Exception
    0.48
     Phenomen
    0.47
     Reaktion
    0.47
    Act Density 0.011%

    No Known Activations