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

    Neuronpedia

    INDEX
    Explanations

    code and punctuation separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     patitth
    0.30
     sabbam
    0.29
     vacanam
    0.28
     vutta
    0.27
    ifestyle
    0.26
     entusiasmo
    0.26
     saddhim
    0.26
    avacanam
    0.26
     faptul
    0.26
     mostrou
    0.26
    POSITIVE LOGITS
    \
    0.32
     tuple
    0.29
    _
    0.29
     +
    0.28
    /
    0.28
     operands
    0.27
    ,
    0.27
    .
    0.26
     angled
    0.26
    ।
    0.26
    Act Density 0.118%

    No Known Activations