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

    Neuronpedia

    INDEX
    Explanations

    Wireless communication technology

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric tokens (especially decimal numbers), i.e. measurement or data values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _property
    -0.07
     datingsider
    -0.06
     withStyles
    -0.06
     झ
    -0.06
    "testing
    -0.06
     числа
    -0.06
    _LOWER
    -0.06
    ?>><?
    -0.06
    政
    -0.06
    album
    -0.06
    POSITIVE LOGITS
     inventory
    0.07
    inium
    0.07
    ekli
    0.07
     cumulative
    0.07
     Mystic
    0.07
    heritance
    0.06
    .badlogic
    0.06
    ilingual
    0.06
    ilmiştir
    0.06
    Germany
    0.06
    Act Density 0.127%

    No Known Activations