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

    Neuronpedia

    INDEX
    Explanations

    code/math notation

    np_max-act · gemini-2.0-flash

    The neuron detects C/C++ header‐include directives (the “#include <…>” tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -even
    -0.07
     Safe
    -0.07
     drilled
    -0.07
    kü
    -0.07
     Om
    -0.07
    aterial
    -0.06
     Float
    -0.06
     TRAIN
    -0.06
    ryfall
    -0.06
     Jake
    -0.06
    POSITIVE LOGITS
    SPA
    0.08
    ёл
    0.06
    .numberOfLines
    0.06
    Gal
    0.06
     rozší
    0.06
     INCLUDE
    0.06
    nofollow
    0.06
     apo
    0.06
    .SelectedItems
    0.06
    .Result
    0.06
    Act Density 0.103%

    No Known Activations