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

    Neuronpedia

    INDEX
    Explanations

    url

    np_max-act · gemini-2.0-flash

    The neuron fires on floating‐point numeric literals embedded in code snippets (i.e. decimal numbers in the JavaScript/Ajax examples).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ennial
    -0.07
    _behavior
    -0.06
    @property
    -0.06
    .setSize
    -0.06
    เศษ
    -0.06
     UPPER
    -0.06
     wor
    -0.06
    _buf
    -0.06
     Various
    -0.06
     शक
    -0.06
    POSITIVE LOGITS
    ais
    0.06
     hunting
    0.06
    Comm
    0.06
     sailed
    0.06
    .getItemId
    0.06
    lius
    0.06
    ammo
    0.06
    izontally
    0.06
    ounder
    0.06
    -faced
    0.06
    Act Density 0.001%

    No Known Activations