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

    Neuronpedia

    INDEX
    Explanations

    party game suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ন
    0.56
     Edd
    0.54
     a
    0.52
     an
    0.52
    ある
    0.52
     Howard
    0.47
    zzi
    0.47
    不存在
    0.46
    arrage
    0.46
    spray
    0.46
    POSITIVE LOGITS
    ।*
    0.57
     물질
    0.57
     материал
    0.55
     চাহিয়
    0.55
     materiale
    0.54
     materiali
    0.54
     ilmiah
    0.54
     दवाई
    0.54
     집
    0.53
     मैट्र
    0.53
    Act Density 0.000%

    No Known Activations