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

    Neuronpedia

    INDEX
    Explanations

    numbers and source code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.91
    ्स
    0.76
    致力于
    0.76
     Gericht
    0.75
     l
    0.72
    '></
    0.72
    proyecto
    0.72
     ferramenta
    0.71
     SignUp
    0.71
     Plattform
    0.71
    POSITIVE LOGITS
    тың
    0.75
     ਅਤੇ
    0.73
     طويل
    0.72
     וי
    0.71
     және
    0.71
     белән
    0.71
    ת
    0.71
     ۽
    0.69
     അത
    0.68
     nhiên
    0.68
    Act Density 0.014%

    No Known Activations