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

    Neuronpedia

    INDEX
    Explanations

    personally identifiable information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     família
    0.51
     querem
    0.49
     zwei
    0.48
     hennes
    0.47
     czter
    0.47
     undulating
    0.47
     pyaar
    0.46
     millió
    0.46
     soooo
    0.46
     famille
    0.45
    POSITIVE LOGITS
    𝗲
    0.49
    ש
    0.46
    О
    0.46
     언급
    0.44
    किसी
    0.43
    \
    0.43
    со
    0.42
    引用
    0.42
    endor
    0.42
    го
    0.42
    Act Density 0.010%

    No Known Activations