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

    Neuronpedia

    INDEX
    Explanations

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     当前
    0.40
    作为
    0.39
     tele
    0.38
    所有的
    0.38
    tele
    0.38
     Todos
    0.37
     但是
    0.37
     mysqli
    0.37
    стное
    0.36
    ందని
    0.36
    POSITIVE LOGITS
     supon
    0.44
     decreed
    0.42
     tradu
    0.41
    ंटिक
    0.41
     සහ
    0.40
    paround
    0.40
     forbind
    0.39
     Stoff
    0.39
     extin
    0.39
     Rücken
    0.39
    Act Density 0.003%

    No Known Activations