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

    Neuronpedia

    INDEX
    Explanations

    .PIPE

    np_max-act · gemini-2.0-flash

    This neuron detects floating-point numeric literals (numbers containing a decimal point) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .listFiles
    -0.07
     extracts
    -0.07
     frække
    -0.06
     alma
    -0.06
     startIndex
    -0.06
    ?$
    -0.06
     हव
    -0.06
    ToOne
    -0.06
    -simple
    -0.06
     Ratings
    -0.06
    POSITIVE LOGITS
    .PIPE
    0.09
    교
    0.07
    ="";
↵
    0.07
     تصميم
    0.07
     अपर
    0.06
     hoạt
    0.06
    اي
    0.06
    pile
    0.06
    Compile
    0.06
    .rc
    0.06
    Act Density 0.000%

    No Known Activations