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

    Neuronpedia

    INDEX
    Explanations

    various licensing options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     euh
    0.44
     butane
    0.44
    S
    0.44
     films
    0.43
     responsibly
    0.43
     effectively
    0.43
     корре
    0.42
     logic
    0.42
     dutiful
    0.42
    М
    0.41
    POSITIVE LOGITS
    ന്ത്രാ
    0.49
    inicio
    0.49
    ulatus
    0.47
    ⎜
    0.47
    insights
    0.46
    }{
    0.45
    рін
    0.45
     पटक
    0.44
    ২৯
    0.44
    သုံးပြု
    0.43
    Act Density 0.000%

    No Known Activations