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

    Neuronpedia

    INDEX
    Explanations

    Nirvana, Colbert, Schubert, libertarian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    栳
    -3.00
    鉺
    -2.94
    廡
    -2.72
    乆
    -2.66
    羮
    -2.61
    蠵
    -2.61
    釕
    -2.58
     خودت
    -2.52
    ㈬
    -2.52
     baden
    -2.48
    POSITIVE LOGITS
    o
    3.20
     If
    2.53
    k
    2.48
    L
    2.47
     unruly
    2.45
     While
    2.39
    hline
    2.38
    2.31
     unrelenting
    2.31
     or
    2.30
    Act Density 0.010%

    No Known Activations