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

    Neuronpedia

    INDEX
    Explanations

    birth years and death years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     problem
    0.96
    不同的
    0.95
    it
    0.93
    roids
    0.86
    不同
    0.86
    angs
    0.86
    oles
    0.85
    ole
    0.84
    amini
    0.84
    新的
    0.83
    POSITIVE LOGITS
     meninggal
    1.06
     cuja
    1.06
     умира
    1.05
     enfermo
    1.03
     cuya
    1.02
     asesin
    0.99
     enfermos
    0.98
     viviendo
    0.96
     умер
    0.96
     morrer
    0.96
    Act Density 0.028%

    No Known Activations