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

    Neuronpedia

    INDEX
    Explanations

    physical harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.76
    DW
    0.66
    unku
    0.64
    Xia
    0.63
    ventus
    0.63
    ヨン
    0.62
    тім
    0.62
    主な
    0.62
    Jl
    0.61
    has
    0.61
    POSITIVE LOGITS
     injuries
    1.34
     injury
    1.14
    伤
    1.05
     bruises
    0.98
    受伤
    0.97
     heridas
    0.96
     повре
    0.96
     Injuries
    0.95
     wounds
    0.95
     Injury
    0.94
    Act Density 0.091%

    No Known Activations