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

    Neuronpedia

    INDEX
    Explanations

    = or :

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point numeric literals (decimal constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     foto
    -0.06
     staff
    -0.06
     Clear
    -0.06
    (int
    -0.06
     surgery
    -0.06
     opport
    -0.06
     Vertex
    -0.06
    scenario
    -0.06
     restart
    -0.06
     admission
    -0.06
    POSITIVE LOGITS
    .Widget
    0.07
     美
    0.07
    isle
    0.07
     předmět
    0.06
     —
    0.06
    lle
    0.06
     ―
    0.06
    ?
    0.06
     trval
    0.06
     dục
    0.06
    Act Density 0.028%

    No Known Activations