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

    Neuronpedia

    INDEX
    Explanations

    what is/why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    丽
    0.48
    ሉም
    0.46
    独特的
    0.46
    时代
    0.45
    椂
    0.43
    زين
    0.43
    财
    0.43
    ра
    0.42
    莱
    0.42
    стер
    0.41
    POSITIVE LOGITS
    ranged
    0.49
    cloth
    0.45
    devi
    0.44
    phones
    0.44
    mechanism
    0.43
    lsulfanyl
    0.42
    index
    0.42
    between
    0.42
     iteratively
    0.42
    div
    0.41
    Act Density 0.003%

    No Known Activations