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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notations related to statistical models and matrices

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

    Hadamard product notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arounds
    -0.45
    nius
    -0.43
     offenses
    -0.42
    thood
    -0.41
    意
    -0.40
    UnsafeEnabled
    -0.39
    parate
    -0.39
    nyk
    -0.39
    ècie
    -0.38
    aim
    -0.38
    POSITIVE LOGITS
     للاسماء
    0.56
    WireFormatLite
    0.49
    IsContent
    0.44
    aarrggbb
    0.44
    writeFieldEnd
    0.43
    parseDouble
    0.43
     BoxDecoration
    0.42
     Biôgrafia
    0.42
     inhoud
    0.42
    MessageTagHelper
    0.41
    Act Density 0.556%

    No Known Activations