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

    Neuronpedia

    INDEX
    Explanations

    comparisons and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    0.95
    ל
    0.88
     Однако
    0.85
     tasma
    0.84
     Интернет
    0.84
     Глав
    0.84
    ματα
    0.83
     ενός
    0.83
    jų
    0.83
    न
    0.83
    POSITIVE LOGITS
     contributing
    0.86
    嗟
    0.82
    ぉ
    0.82
    mentioned
    0.81
     schon
    0.79
    음
    0.79
    귀
    0.79
    け
    0.77
    ాగ
    0.75
     Bela
    0.73
    Act Density 0.002%

    No Known Activations