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

    Neuronpedia

    INDEX
    Explanations

    beginner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ஜன்
    0.80
     complement
    0.72
     अग्र
    0.71
     транспорти
    0.68
     কিছুক্ষণ
    0.67
     transport
    0.67
    对了
    0.67
    踊
    0.66
    鏗
    0.65
    TRAS
    0.64
    POSITIVE LOGITS
    ishly
    0.87
    ussa
    0.77
    |$
    0.73
     lukewarm
    0.70
    Ish
    0.68
    abbam
    0.67
    ISH
    0.67
     Jess
    0.67
     Kol
    0.66
    Jess
    0.66
    Act Density 0.033%

    No Known Activations