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

    Neuronpedia

    INDEX
    Explanations

    appearance and disappearance

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens containing decimal points, i.e. floating-point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Playback
    -0.06
     decoder
    -0.06
     integrity
    -0.06
    _mock
    -0.06
     true
    -0.06
    _test
    -0.06
    изнес
    -0.06
    (dl
    -0.06
     navigating
    -0.06
     保
    -0.06
    POSITIVE LOGITS
     catholic
    0.07
     Carnegie
    0.07
     国家
    0.07
     Sheikh
    0.07
    .sqrt
    0.07
     Colo
    0.07
    ังหว
    0.06
    ;:
    0.06
    ethyst
    0.06
    ['__
    0.06
    Act Density 0.067%

    No Known Activations