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

    Neuronpedia

    INDEX
    Explanations

    here are some

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كامل
    0.71
     Именно
    0.68
     कोणत्याही
    0.65
    ∵
    0.63
     مهما
    0.62
     بكل
    0.62
     rimane
    0.62
    圧倒
    0.62
     تمام
    0.62
     gesamte
    0.61
    POSITIVE LOGITS
     some
    5.45
    some
    4.60
    Some
    4.52
     Some
    4.50
    一些
    4.39
     بعض
    4.23
     algunos
    4.20
     alguns
    4.17
     algunas
    4.14
     einige
    4.04
    Act Density 1.109%

    No Known Activations