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

    Neuronpedia

    INDEX
    Explanations

    backslash

    np_max-act · gemini-2.0-flash

    The neuron is specialized to pick out floating‐point number literals (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ButtonModule
    -0.07
    Ray
    -0.07
     cosm
    -0.06
     sle
    -0.06
    یط
    -0.06
     aliqu
    -0.06
     économ
    -0.06
    anten
    -0.06
     cục
    -0.06
     CS
    -0.06
    POSITIVE LOGITS
    .pitch
    0.07
     ^↵
    0.06
    ehicle
    0.06
     `↵
    0.06
     ")"↵
    0.06
    Blockchain
    0.06
    .addAttribute
    0.06
    _SETUP
    0.06
    bn
    0.06
     ра�
    0.06
    Act Density 0.011%

    No Known Activations