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

    Neuronpedia

    INDEX
    Explanations

    conditional logic and flexibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     minify
    0.50
     fray
    0.47
     sam
    0.44
    cpy
    0.43
     estup
    0.42
     uang
    0.42
     manches
    0.41
     monotony
    0.41
    部
    0.41
     bouts
    0.40
    POSITIVE LOGITS
    IBILITY
    0.48
     Universitario
    0.46
     Сьогодні
    0.45
    和社会
    0.44
    <unused342>
    0.44
    <unused248>
    0.43
    anthropy
    0.43
    <unused632>
    0.42
    <unused1150>
    0.42
     स्लाइड्स
    0.42
    Act Density 0.001%

    No Known Activations