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

    Neuronpedia

    INDEX
    Explanations

    without explicit content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.75
    ’
    0.68
     ﺍﻟ
    0.57
     \
    0.57
     straighten
    0.56
     reimburse
    0.56
    <i>
    0.54
     vorhanden
    0.54
    ological
    0.54
     ."
    0.53
    POSITIVE LOGITS
    without
    0.73
    ور
    0.70
     Without
    0.66
    ذ
    0.63
    Without
    0.62
     without
    0.61
    hattim
    0.61
     incurring
    0.59
    ת
    0.59
    ت
    0.58
    Act Density 0.076%

    No Known Activations