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

    Neuronpedia

    INDEX
    Explanations

    (*

    np_max-act · gemini-2.0-flash

    The neuron selectively lights up on floating‐point numeric literals (decimal constants) in the source.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .nasa
    -0.07
    _-_
    -0.07
    KIT
    -0.06
    ayın
    -0.06
     ссыл
    -0.06
     Mori
    -0.06
    accion
    -0.06
    ्ल
    -0.06
    _now
    -0.06
    con
    -0.06
    POSITIVE LOGITS
    .setPosition
    0.07
     §
    0.07
     leading
    0.06
     신입
    0.06
     Ethiopian
    0.06
    Despite
    0.06
    urchases
    0.06
    (prev
    0.06
     ';'
    0.06
    [['
    0.06
    Act Density 0.001%

    No Known Activations