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

    Neuronpedia

    INDEX
    Explanations

    x + addition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лень
    0.44
    bP
    0.44
    adığı
    0.43
    र्सन
    0.41
    outcome
    0.41
    desk
    0.40
    Berk
    0.39
    đe
    0.39
    ലിം
    0.39
    forms
    0.39
    POSITIVE LOGITS
     $+
    0.63
     +
    0.57
    +
    0.54
     הפר
    0.43
     $+\
    0.43
     Alone
    0.43
     plus
    0.42
     以及
    0.42
     Variable
    0.42
     Months
    0.41
    Act Density 0.018%

    No Known Activations