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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbers or division

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.65
     queſta
    -0.58
     يتيمه
    -0.57
     للمعارف
    -0.56
     viewDidLoad
    -0.55
    PyExc
    -0.55
     initializer
    -0.54
    <unused23>
    -0.54
    <unused8>
    -0.53
    <unused79>
    -0.53
    POSITIVE LOGITS
     zwei
    0.47
    two
    0.44
     TWO
    0.43
     dobles
    0.43
     DOUBLE
    0.43
    zwei
    0.42
    DOUBLE
    0.42
    TWO
    0.41
    Zwei
    0.41
    Two
    0.41
    Act Density 0.460%

    No Known Activations