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

    Neuronpedia

    INDEX
    Explanations

    time and its usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    th
    0.45
    w
    0.45
    v
    0.45
    h
    0.43
     outputs
    0.41
     axons
    0.41
    id
    0.41
    line
    0.41
    x
    0.41
    k
    0.40
    POSITIVE LOGITS
     allotted
    0.76
     consacré
    0.63
     فرص
    0.63
     dedicar
    0.63
     dedicato
    0.61
     timeLeft
    0.60
     시간을
    0.59
     Allocated
    0.58
     dedicata
    0.58
     devoting
    0.58
    Act Density 0.082%

    No Known Activations