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

    Neuronpedia

    INDEX
    Explanations

    approaching words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.81
     Grief
    0.77
     Leverage
    0.77
    ană
    0.76
     Deter
    0.75
    freien
    0.75
    씀
    0.73
     Open
    0.73
    สเตอร์
    0.72
    เพียง
    0.71
    POSITIVE LOGITS
     лі
    0.87
     toa
    0.86
     morph
    0.83
    Claire
    0.83
    氇
    0.83
    Перед
    0.82
    dı
    0.81
    І
    0.81
    iz
    0.79
     diz
    0.79
    Act Density 0.000%

    No Known Activations