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

    Neuronpedia

    INDEX
    Explanations

    death and loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    焚
    0.43
     যাবতীয়
    0.41
     неуда
    0.40
    ths
    0.38
    vre
    0.38
     incriminating
    0.38
     मालूम
    0.37
    trivial
    0.37
    back
    0.37
    mv
    0.37
    POSITIVE LOGITS
     falleció
    0.82
    逝
    0.79
     deceased
    0.75
    deceased
    0.71
     décès
    0.71
    去世
    0.71
     departed
    0.66
     mortality
    0.65
     meninggal
    0.62
     death
    0.58
    Act Density 0.026%

    No Known Activations