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

    Neuronpedia

    INDEX
    Explanations

    measurements and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AgNO
    0.50
     Modell
    0.48
    <unused2017>
    0.48
    <unused601>
    0.48
     międzynarod
    0.47
     niemie
    0.47
     እንደሚ
    0.46
    同学们
    0.46
    이사
    0.46
    <unused622>
    0.46
    POSITIVE LOGITS
    OF
    0.46
    have
    0.46
     tan
    0.45
     db
    0.43
     nozzle
    0.43
     %
    0.42
    UMS
    0.42
    '
    0.42
    Per
    0.42
    $
    0.41
    Act Density 0.003%

    No Known Activations