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

    Neuronpedia

    INDEX
    Explanations

    links like instagram and facebook

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ar
    0.63
    ning
    0.58
    nerv
    0.57
    wald
    0.56
    arci
    0.55
    labyrinth
    0.55
    aine
    0.55
    corp
    0.55
    ♲
    0.55
    t
    0.54
    POSITIVE LOGITS
    ي
    0.79
    י
    0.70
     décadas
    0.58
    레
    0.57
    ми
    0.55
    连忙
    0.55
    ে
    0.55
    يتر
    0.54
    ري
    0.54
    шем
    0.54
    Act Density 0.004%

    No Known Activations