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

    Neuronpedia

    INDEX
    Explanations

    actions followed by continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     любых
    0.43
    ometimes
    0.41
    Nodes
    0.41
     любые
    0.40
    ють
    0.40
     denominations
    0.39
    ﻌ
    0.39
    have
    0.39
     мають
    0.39
     effic
    0.39
    POSITIVE LOGITS
     очередной
    0.59
     an
    0.57
     during
    0.55
     accidentally
    0.54
     sebuah
    0.54
     celebrating
    0.51
     carelessly
    0.50
     очеред
    0.50
    حدى
    0.48
     einer
    0.47
    Act Density 0.069%

    No Known Activations