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

    Neuronpedia

    INDEX
    Explanations

    java set and collection types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enumerated
    0.39
     Weib
    0.36
    Mip
    0.34
     harnessed
    0.33
     harness
    0.33
    代言
    0.32
     prolong
    0.32
     NGC
    0.32
     eclipsed
    0.32
     Mn
    0.31
    POSITIVE LOGITS
    🙉
    0.44
    innest
    0.44
    royo
    0.42
    schod
    0.41
    emper
    0.40
     Почему
    0.40
     Ото
    0.40
     desar
    0.40
    empor
    0.40
    !("{}",
    0.39
    Act Density 0.002%

    No Known Activations