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

    Neuronpedia

    INDEX
    Explanations

    streaming database

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hers
    0.42
     kesin
    0.41
     Hul
    0.41
     Missile
    0.41
     Terms
    0.40
     sdl
    0.40
     الجنوب
    0.39
     South
    0.38
     sle
    0.38
    随意
    0.38
    POSITIVE LOGITS
     фрук
    0.46
     Pisa
    0.44
     Carrick
    0.43
    দ্ম
    0.43
    isah
    0.42
    aur
    0.42
    Bend
    0.41
     realise
    0.40
    romad
    0.40
     Bend
    0.39
    Act Density 0.001%

    No Known Activations