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

    Neuronpedia

    INDEX
    Explanations

    supportive gear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     foreground
    0.85
     pli
    0.80
     prélim
    0.71
     külön
    0.70
     minu
    0.69
     intern
    0.69
     interns
    0.68
     منی
    0.68
     stanow
    0.66
    軽く
    0.66
    POSITIVE LOGITS
    Swimming
    0.82
    薔
    0.79
     Swimming
    0.77
     Volleyball
    0.76
    Shoes
    0.74
    явля
    0.73
    Year
    0.68
    Mens
    0.66
    trend
    0.66
     Alphabet
    0.66
    Act Density 0.001%

    No Known Activations