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

    Neuronpedia

    INDEX
    Explanations

    code generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.73
    ،
    0.59
     in
    0.52
    ی
    0.47
    ,
    0.46
     어린
    0.44
     collecting
    0.44
     여러분
    0.43
    在
    0.42
    एक
    0.42
    POSITIVE LOGITS
    كر
    0.79
    اکي
    0.74
    وري
    0.66
    يرة
    0.64
    اي
    0.63
     novembre
    0.63
    يده
    0.63
     نہيں
    0.63
     foglie
    0.62
    ется
    0.61
    Act Density 0.000%

    No Known Activations