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

    Neuronpedia

    INDEX
    Explanations

    /tmp/ file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ра
    1.77
    众多
    1.49
     nouvelle
    1.48
    ài
    1.45
     vallée
    1.43
     laquelle
    1.38
    년대
    1.38
    ದ್ಧ
    1.38
    StudentNo
    1.32
    他在
    1.31
    POSITIVE LOGITS
    l
    1.90
    ف
    1.83
    mers
    1.73
    ان
    1.65
    m
    1.64
    ب
    1.52
    ন
    1.51
    meg
    1.48
    lc
    1.48
    liness
    1.48
    Act Density 0.004%

    No Known Activations