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

    Neuronpedia

    INDEX
    Explanations

    following 'of'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '.
    0.37
     Aspects
    0.36
    by
    0.36
    ':
    0.35
    Various
    0.35
     etc
    0.34
     Using
    0.34
    also
    0.34
    /
    0.34
    間
    0.34
    POSITIVE LOGITS
     interest
    0.55
     Interesse
    0.49
     course
    0.48
     interesse
    0.43
    intérêt
    0.43
     interés
    0.41
     इंटरेस्ट
    0.41
    interest
    0.39
    Interest
    0.38
     thei
    0.38
    Act Density 0.160%

    No Known Activations