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

    Neuronpedia

    INDEX
    Explanations

    quality clip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نیچے
    0.51
    сь
    0.49
     consec
    0.48
     کمپیوٹر
    0.47
     सीखने
    0.46
    ೊಳ
    0.45
    luk
    0.45
     рік
    0.45
    iselle
    0.44
     گوئیاں
    0.43
    POSITIVE LOGITS
     pourtant
    0.57
     are
    0.50
    俆
    0.46
    ्याने
    0.46
     difund
    0.44
     diantaranya
    0.44
    χος
    0.43
    These
    0.43
    Are
    0.43
     tamen
    0.43
    Act Density 0.000%

    No Known Activations