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

    Neuronpedia

    INDEX
    Explanations

    C programming code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     new
    0.85
     neuen
    0.82
     neue
    0.80
    new
    0.79
     nieuwe
    0.76
     новые
    0.75
    새
    0.72
     নতুন
    0.72
     nuovo
    0.71
     بدی
    0.70
    POSITIVE LOGITS
     berk
    0.70
     இருக்கிறார்
    0.69
    ويات
    0.67
    溸
    0.66
     definida
    0.65
     आध्यात्म
    0.65
     DMR
    0.64
     وهي
    0.64
    庾
    0.63
     وهنا
    0.63
    Act Density 0.025%

    No Known Activations