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

    Neuronpedia

    INDEX
    Explanations

    Got Mail!

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    1.04
    न
    0.80
    ك
    0.74
    ت
    0.73
    ন
    0.72
    н
    0.67
    ン
    0.64
    nak
    0.60
    т
    0.57
    त
    0.56
    POSITIVE LOGITS
    𝕡
    0.54
     competencia
    0.54
    쐞
    0.53
    ⓪
    0.53
    йна
    0.53
    하다
    0.53
    üğünüz
    0.53
    ის
    0.52
     textual
    0.51
    の中心
    0.51
    Act Density 0.000%

    No Known Activations