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

    Neuronpedia

    INDEX
    Explanations

    code in various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Yes
    0.72
    Parsed
    0.71
    Roses
    0.69
    Anyone
    0.68
     tra
    0.67
     নিমিত
    0.66
    Wil
    0.65
     sex
    0.65
     neighboring
    0.64
    ार्मिक
    0.62
    POSITIVE LOGITS
    <end_of_turn>
    1.05
    rrbracket
    0.82
    codigo
    0.78
    皓
    0.77
    十五章
    0.76
    <unused70>
    0.75
    코드
    0.74
     コード
    0.74
    marco
    0.73
    码
    0.72
    Act Density 0.250%

    No Known Activations