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

    Neuronpedia

    INDEX
    Explanations

    continuations, elaborations, or results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.45
     ८
    0.44
     ৪
    0.43
    for
    0.42
     tenía
    0.40
     X
    0.40
     ৬
    0.40
    4
    0.39
    ров
    0.39
    その
    0.39
    POSITIVE LOGITS
     tireless
    0.47
    지와
    0.44
    ing
    0.44
     mesmer
    0.43
    al
    0.41
     mesmerizing
    0.41
     Featuring
    0.39
    د
    0.39
     असून
    0.38
     companionship
    0.38
    Act Density 0.001%

    No Known Activations