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

    Neuronpedia

    INDEX
    Explanations

    C++ code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    थाल
    0.68
    ⑵
    0.63
     Elektrokh
    0.62
     foie
    0.62
    नेटरी
    0.62
    嗳
    0.62
     الأ
    0.59
    الوج
    0.59
    uszt
    0.59
    纱
    0.58
    POSITIVE LOGITS
     C
    4.75
    C
    4.38
     c
    4.38
    c
    3.96
    Ｃ
    3.18
    setC
    2.90
    ｃ
    2.82
    𝐶
    2.65
    ᴄ
    2.54
    𝑪
    2.52
    Act Density 1.017%

    No Known Activations