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

    Neuronpedia

    INDEX
    Explanations

    body piercings and modification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    癃
    0.70
    榫
    0.62
    ј
    0.60
    мо
    0.59
    movie
    0.58
    же
    0.57
    p
    0.56
    ке
    0.55
    ewnętr
    0.55
    пы
    0.54
    POSITIVE LOGITS
     alcal
    0.59
     egyéb
    0.49
    ãy
    0.47
     regex
    0.47
    ’।
    0.47
     apiUrl
    0.47
     कैंड
    0.46
     whistles
    0.46
     not
    0.46
     candid
    0.45
    Act Density 0.003%

    No Known Activations