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

    Neuronpedia

    INDEX
    Explanations

    concave lens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    वेयर
    0.50
    ネルギー
    0.49
    รียน
    0.48
    形成
    0.47
    FlashValue
    0.47
    стой
    0.47
     volunteered
    0.46
    ंडीज
    0.46
     ഇടപെ
    0.46
    ರ
    0.46
    POSITIVE LOGITS
     Bill
    0.44
    em
    0.43
    UR
    0.42
    M
    0.42
    ali
    0.41
    alen
    0.41
     فيما
    0.41
    nh
    0.41
     Martini
    0.40
    ...
    0.40
    Act Density 0.001%

    No Known Activations