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

    Neuronpedia

    INDEX
    Explanations

    limit and integral notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лейбол
    0.44
     घेण्यासाठी
    0.42
    ίνη
    0.40
    어요
    0.39
    ъм
    0.39
    горь
    0.39
    écie
    0.38
    िणी
    0.38
    annuation
    0.38
    อะคาเดมี
    0.37
    POSITIVE LOGITS
     of
    0.49
     vutta
    0.42
    (
    0.40
     C
    0.40
     急
    0.40
    _{
    0.39
    {
    0.38
    ((
    0.38
     của
    0.37
    of
    0.36
    Act Density 0.019%

    No Known Activations