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

    Neuronpedia

    INDEX
    Explanations

    right now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thence
    0.41
     poi
    0.40
    ෝග
    0.35
     baffling
    0.34
     eventually
    0.34
    poi
    0.34
    Modern
    0.34
    setP
    0.33
    Previous
    0.32
    heen
    0.32
    POSITIVE LOGITS
     сейчас
    2.69
     지금
    2.30
     Сейчас
    2.09
    Сейчас
    2.08
    現在
    2.06
    지금
    2.03
     currently
    1.98
    现在
    1.98
     presently
    1.94
     현재
    1.94
    Act Density 0.046%

    No Known Activations