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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals in code (e.g., “2.923828125”, “0.669921875”, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _po
    -0.07
    alt
    -0.07
    -B
    -0.07
     ridden
    -0.06
    飯
    -0.06
    getDrawable
    -0.06
    *pi
    -0.06
    EMU
    -0.06
    dG
    -0.06
     Gate
    -0.06
    POSITIVE LOGITS
    .boolean
    0.06
    之后
    0.06
     trái
    0.06
     provinces
    0.06
     soğuk
    0.05
     wake
    0.05
     Ingredient
    0.05
    !'
    0.05
    edReader
    0.05
    .SelectedItems
    0.05
    Act Density 0.008%

    No Known Activations