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

    Neuronpedia

    INDEX
    Explanations

    interest and accrual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dist
    0.72
    时候
    0.69
     व
    0.67
     kust
    0.65
    话
    0.65
     dim
    0.63
     estou
    0.63
    }^{-\
    0.63
    ה
    0.63
     exceso
    0.63
    POSITIVE LOGITS
    ଃ
    0.79
    ري
    0.72
     AppComponent
    0.72
    釟
    0.72
     từng
    0.68
    «.
    0.68
    த்ரே
    0.67
     유형
    0.66
    úde
    0.66
     활용
    0.66
    Act Density 0.030%

    No Known Activations