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

    Neuronpedia

    INDEX
    Explanations

    scientific research papers

    np_max-act · gemini-2.0-flash

    The neuron detects floating‐point numerical values (decimal measurements) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _stop
    -0.06
     found
    -0.06
     prevalent
    -0.06
    udd
    -0.06
    pres
    -0.06
    탁
    -0.06
     vua
    -0.06
     manual
    -0.06
    hw
    -0.06
     picnic
    -0.06
    POSITIVE LOGITS
    (Http
    0.08
    (dim
    0.07
     الذ
    0.06
    256
    0.06
     dök
    0.06
     $("<
    0.06
     CHUNK
    0.06
    storms
    0.06
    .services
    0.06
    nombre
    0.06
    Act Density 0.100%

    No Known Activations