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

    Neuronpedia

    INDEX
    Explanations

    # comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ദം
    0.42
    罅
    0.39
    䤃
    0.37
    त
    0.36
    భ
    0.36
    Fitting
    0.35
    fé
    0.34
    Flex
    0.34
     femei
    0.34
    امات
    0.34
    POSITIVE LOGITS
     <!--<
    0.58
    ;//
    0.57
     invece
    0.55
     instead
    0.54
     Instead
    0.54
     পরিবর্তে
    0.54
    /*
    0.52
    Instead
    0.50
     ejemplos
    0.49
     대신
    0.48
    Act Density 0.183%

    No Known Activations