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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash

    This neuron detects floating-point constants—that is, numeric tokens representing decimal‐point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Rare
    -0.06
    .Resources
    -0.06
     Hunt
    -0.06
    @app
    -0.06
     bush
    -0.06
     Perez
    -0.06
    _mapper
    -0.06
    영상
    -0.06
    fcntl
    -0.06
    $
    -0.06
    POSITIVE LOGITS
     cmds
    0.06
     shortly
    0.06
     allot
    0.06
     atl
    0.06
     odst
    0.06
    .setProgress
    0.06
    Bài
    0.06
    .Println
    0.06
     flavours
    0.06
     Quando
    0.06
    Act Density 0.025%

    No Known Activations