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

    Neuronpedia

    INDEX
    Explanations

    Scientific texts

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric measurements—especially decimal number tokens (e.g., “0.35,” “1.83,” “0.5127,” etc.) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    687
    -0.07
     vbox
    -0.06
     antenna
    -0.06
    níky
    -0.06
    duced
    -0.06
    odium
    -0.06
     nationalism
    -0.06
    /device
    -0.06
     në
    -0.06
    apses
    -0.06
    POSITIVE LOGITS
    _regular
    0.08
     Таким
    0.07
    .::.::
    0.06
    .username
    0.06
     MULTI
    0.06
     iso
    0.06
    (symbol
    0.06
     Phó
    0.06
    _my
    0.06
    using
    0.06
    Act Density 0.413%

    No Known Activations