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

    Neuronpedia

    INDEX
    Explanations

    .h

    np_max-act · gemini-2.0-flash

    This neuron detects references to C/C++ header files, i.e. “.h” include paths.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    课
    -0.07
    ()){↵
    -0.07
    /base
    -0.07
    So
    -0.06
    ）。
    -0.06
    猜
    -0.06
     Encore
    -0.06
    /********************************************************
    -0.06
     言
    -0.06
     chica
    -0.06
    POSITIVE LOGITS
    〇
    0.07
    mk
    0.06
    lb
    0.06
    RK
    0.06
    .graphics
    0.06
    вер
    0.06
     (
↵
    0.06
    لیم
    0.06
    -final
    0.05
     pledges
    0.05
    Act Density 0.010%

    No Known Activations