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

    Neuronpedia

    INDEX
    Explanations

    terms followed by abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oc
    0.50
    ure
    0.48
    url
    0.45
    ive
    0.43
    ads
    0.43
    mp
    0.43
    arta
    0.42
    ুকের
    0.42
    ank
    0.42
    case
    0.41
    POSITIVE LOGITS
    简称
    0.61
     $(\
    0.60
    '(
    0.54
     '(
    0.52
     abbreviated
    0.52
     (°
    0.52
     }(\
    0.51
     $($
    0.45
     berjudul
    0.43
     (
    0.43
    Act Density 0.526%

    No Known Activations