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

    Neuronpedia

    INDEX
    Explanations

    Avengers Assemble

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ва
    0.57
    schule
    0.52
    க்கழக
    0.52
    vertrag
    0.52
     rapeseed
    0.52
    ان
    0.51
     titanium
    0.50
    ഷണ
    0.50
    ങ്ങളും
    0.50
     dioxide
    0.49
    POSITIVE LOGITS
    '
    0.53
     fois
    0.51
    obile
    0.51
     спра
    0.49
    ਮ
    0.49
    ,{\
    0.48
     arterioles
    0.48
    Preg
    0.48
    to
    0.47
     handel
    0.46
    Act Density 0.000%

    No Known Activations