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

    Neuronpedia

    INDEX
    Explanations

    c# code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಸ್ಕೊ
    1.92
     što
    1.86
     reputed
    1.75
    eris
    1.72
    st
    1.71
    ocyte
    1.69
    ัน
    1.68
     আওতায়
    1.67
    ść
    1.67
    erade
    1.64
    POSITIVE LOGITS
    𝑏
    1.73
    មើ
    1.58
    애
    1.56
    𝐺
    1.52
     Repeating
    1.52
    𝑘
    1.52
    𝑎
    1.52
    ン
    1.48
    𝑠
    1.47
     Bás
    1.46
    Act Density 0.001%

    No Known Activations