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

    Neuronpedia

    INDEX
    Explanations

    It is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0xEE>
    -0.80
     игроков
    -0.79
     scammed
    -0.75
     Universo
    -0.74
     FDI
    -0.73
    arischen
    -0.72
    uintptr
    -0.71
     princi
    -0.71
     crimin
    -0.70
     Carré
    -0.70
    POSITIVE LOGITS
     vacía
    0.75
     explored
    0.73
     what
    0.71
     you
    0.70
    することに
    0.69
     Glance
    0.68
    íte
    0.66
    രു
    0.66
     so
    0.65
     just
    0.65
    Act Density 0.035%

    No Known Activations