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

    Neuronpedia

    INDEX
    Explanations

    numbers and approximations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chit
    0.64
    the
    0.61
    рики
    0.59
    মানে
    0.57
    मिस्ट्री
    0.57
     रुपये
    0.56
    ruits
    0.56
    rically
    0.56
    㭐
    0.55
    ığımız
    0.54
    POSITIVE LOGITS
     około
    0.69
     ۲۰۰
    0.68
     ۱۰
    0.64
     zehn
    0.61
     aproximativ
    0.61
    0.61
     २००
    0.59
     ۱۵
    0.58
     짧
    0.58
     altijd
    0.57
    Act Density 0.001%

    No Known Activations