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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of specialized technical jargon—particularly mathematical and engineering terms (e.g. electrical impedance tomography, Neumann/Dirichlet maps, conductivity, simulations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .listFiles
    -0.07
     Sof
    -0.06
    Dst
    -0.06
    illegal
    -0.06
    ्ल
    -0.06
    odo
    -0.06
     infant
    -0.06
     defender
    -0.06
    τω
    -0.06
     Kaf
    -0.06
    POSITIVE LOGITS
    (KEY
    0.07
    ))[
    0.06
     yield
    0.06
     locom
    0.06
    /',
    0.06
    %).
    0.06
    (deck
    0.06
     اروپ
    0.06
    (matrix
    0.06
     raise
    0.06
    Act Density 0.010%

    No Known Activations