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

    Neuronpedia

    INDEX
    Explanations

    hashtags and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iesi
    0.66
    IDE
    0.63
    ضی
    0.60
    IDER
    0.59
    Screw
    0.59
    i
    0.59
    xg
    0.59
    Callories
    0.59
    Miscellaneous
    0.59
    Tissue
    0.58
    POSITIVE LOGITS
     jól
    0.61
     fél
    0.59
     (
    0.58
     НА
    0.56
     （
    0.55
     В
    0.55
     begitu
    0.54
     begy
    0.53
     спа
    0.52
    公开
    0.52
    Act Density 0.002%

    No Known Activations