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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron detects C/C++ preprocessor include directives and the header‐file path tokens that follow them.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (download
    -0.08
     ugl
    -0.07
    愿
    -0.07
     Additional
    -0.07
    Standard
    -0.06
    �
    -0.06
    �
    -0.06
    ि�
    -0.06
    _tex
    -0.06
    飾
    -0.06
    POSITIVE LOGITS
    =pos
    0.07
     بعدی
    0.07
    吧
    0.06
     Rays
    0.06
     poč
    0.06
    Crear
    0.06
     вищ
    0.06
     Career
    0.06
     Orth
    0.06
    :numel
    0.06
    Act Density 0.148%

    No Known Activations