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

    Neuronpedia

    INDEX
    Explanations

    Ind words and endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bordo
    2.77
     exag
    2.70
     ensued
    2.56
    Не
    2.47
     imponer
    2.40
     heed
    2.39
     enfrent
    2.39
     ordeal
    2.37
    भौ
    2.36
    Οι
    2.31
    POSITIVE LOGITS
    št
    2.77
    旛
    2.55
    ividual
    2.51
    ስቃሴ
    2.39
    偎
    2.32
    ত
    2.25
    ognito
    2.24
     массы
    2.19
    ein
    2.13
    ilizce
    2.13
    Act Density 0.889%

    No Known Activations