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

    Neuronpedia

    INDEX
    Explanations

    elasticsearch index query

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Activation
    0.41
     Alberts
    0.40
    Spl
    0.39
     arche
    0.39
     Arche
    0.39
    Fiber
    0.38
     पाठ
    0.37
    স্ট্র
    0.37
     Livermore
    0.36
     dissected
    0.36
    POSITIVE LOGITS
     index
    0.65
    index
    0.62
    INDEX
    0.60
     scroll
    0.59
     indices
    0.59
     индек
    0.58
     indeks
    0.57
    scroll
    0.57
     INDEX
    0.55
     Indices
    0.54
    Act Density 0.008%

    No Known Activations