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

    Neuronpedia

    INDEX
    Explanations

    decimal number systems and programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Drummond
    0.78
     showering
    0.73
     cooking
    0.69
     masks
    0.69
     अभ
    0.67
     households
    0.67
     friends
    0.67
     costumes
    0.67
     pandemi
    0.66
     Country
    0.65
    POSITIVE LOGITS
    Bootstrap
    0.75
    icial
    0.74
     Alta
    0.72
    getPrice
    0.71
     π
    0.69
     Kurz
    0.67
    Bundle
    0.66
     erset
    0.66
    ുകയായിരുന്നു
    0.65
     दोषी
    0.64
    Act Density 0.000%

    No Known Activations