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

    Neuronpedia

    INDEX
    Explanations

    subject and outcome description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    னே
    0.53
     reiniciar
    0.52
     absur
    0.48
    ື້ນ
    0.47
     comuni
    0.46
    कर्ता
    0.46
     sektor
    0.46
    م
    0.46
     comunidades
    0.46
     statistique
    0.46
    POSITIVE LOGITS
    cos
    0.45
    :
    0.44
    pi
    0.44
    iotsitewise
    0.43
    arms
    0.43
    chen
    0.43
    zw
    0.43
    lover
    0.41
    ,
    0.41
    ：
    0.40
    Act Density 0.001%

    No Known Activations