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

    Neuronpedia

    INDEX
    Explanations

    flares went

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ET
    0.38
     ላይ
    0.37
     Sore
    0.36
    oche
    0.36
    horn
    0.36
     uy
    0.35
     patip
    0.35
    ien
    0.35
     pâ
    0.35
     atan
    0.35
    POSITIVE LOGITS
    श्विक
    0.43
     कोषा
    0.40
    Rq
    0.39
     முடியாது
    0.39
     Haq
    0.38
     حک
    0.37
    REQUI
    0.37
    সম্পাদক
    0.36
    Попис
    0.36
    ﺫ
    0.36
    Act Density 0.000%

    No Known Activations