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

    Neuronpedia

    INDEX
    Explanations

    preview appearance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     أجل
    1.86
     terrible
    1.82
     fumble
    1.76
     செறிவு
    1.73
     بالنسبة
    1.72
     permettre
    1.71
    fscanf
    1.67
     embora
    1.66
    cción
    1.64
     uncon
    1.62
    POSITIVE LOGITS
    ת
    2.45
    }$
    2.24
    en
    2.20
    ্কর
    2.07
    cı
    1.97
    ع
    1.95
    ة
    1.91
    мся
    1.84
    }></
    1.83
    り
    1.80
    Act Density 0.042%

    No Known Activations