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

    Neuronpedia

    INDEX
    Explanations

    assessing what will be done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.57
     schreibt
    0.50
     ξ
    0.48
    ENDS
    0.48
     minhas
    0.48
     куда
    0.48
     izra
    0.47
    скольку
    0.47
     darf
    0.47
     fuertes
    0.46
    POSITIVE LOGITS
    ی
    0.58
    ש
    0.48
    종
    0.48
    솥
    0.48
    ک
    0.47
     اسے
    0.46
    ת
    0.46
     counseling
    0.44
    ü
    0.43
    ಣಿ
    0.43
    Act Density 0.159%

    No Known Activations