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

    Neuronpedia

    INDEX
    Explanations

    their vast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fuertes
    0.70
     istot
    0.66
     Increases
    0.66
     خوبی
    0.65
     khác
    0.65
    非常的
    0.63
     STRONG
    0.63
     Strong
    0.63
     Amounts
    0.62
     Интере
    0.62
    POSITIVE LOGITS
     dilapidated
    1.19
     lonely
    1.13
     hapless
    1.12
     crumbling
    1.11
     ailing
    1.08
     hopelessly
    1.07
     bewildered
    1.07
     unassuming
    1.05
     soggy
    1.05
     impoverished
    1.04
    Act Density 1.104%

    No Known Activations