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

    Neuronpedia

    INDEX
    Explanations

    pain and injury signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     befri
    0.39
     Sext
    0.39
     fundraisers
    0.38
    insurance
    0.38
    Vit
    0.38
    NetStandard
    0.37
    γει
    0.37
    Docket
    0.37
    bankruptcy
    0.37
     sauvegarde
    0.37
    POSITIVE LOGITS
    疼痛
    0.44
     दर्द
    0.44
     scraping
    0.43
     tingling
    0.42
     pain
    0.41
     Funcion
    0.41
     Chloride
    0.40
     reclining
    0.40
     unwell
    0.39
    痛み
    0.39
    Act Density 0.023%

    No Known Activations