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

    Neuronpedia

    INDEX
    Explanations

    why protons are damaging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     equaliser
    0.42
    စိတ်
    0.39
     ஜோ
    0.38
     kilometres
    0.38
     इनो
    0.38
     неста
    0.38
     Iterable
    0.38
     derive
    0.37
     නිෂ්
    0.37
     hệ
    0.37
    POSITIVE LOGITS
    anu
    0.41
     रामचंद्र
    0.41
    ክር
    0.40
    ছেন
    0.40
    旁的
    0.40
    setStatus
    0.40
    ছে
    0.39
     vouch
    0.39
    Trashed
    0.39
    InChildren
    0.38
    Act Density 0.000%

    No Known Activations