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

    Neuronpedia

    INDEX
    Explanations

    OHLC, Nyitott, iritsi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    туре
    0.41
    𒌅
    0.40
     متحده
    0.38
    тря
    0.38
     韩
    0.38
     \\[
    0.37
    強化
    0.36
     পূর্ববাংলার
    0.36
    垶
    0.36
     ಮುಖ್ಯ
    0.35
    POSITIVE LOGITS
     since
    0.37
    since
    0.34
    Since
    0.33
    oui
    0.32
     solicited
    0.32
     मोहो
    0.32
     blessed
    0.31
     obliged
    0.31
    Ahh
    0.31
     conductor
    0.31
    Act Density 0.001%

    No Known Activations