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

    Neuronpedia

    INDEX
    Explanations

    pre-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     versatility
    0.84
     astron
    0.75
     versatile
    0.73
     country
    0.73
     spear
    0.72
     elf
    0.72
     consecuencia
    0.71
     kep
    0.70
     pyramid
    0.70
     orang
    0.69
    POSITIVE LOGITS
    emptive
    1.17
    cursor
    1.06
    iminary
    1.06
    emption
    1.03
    ceed
    1.02
    determine
    0.98
    vius
    0.94
    centage
    0.94
    eminent
    0.93
    prar
    0.91
    Act Density 0.132%

    No Known Activations