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

    Neuronpedia

    INDEX
    Explanations

    library

    np_max-act · gemini-2.0-flash

    The neuron is triggered by programming-language tokens and code-related syntax, such as “C#,” library names, and other snippet markers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Date
    -0.07
     sit
    -0.07
    Turn
    -0.07
     separate
    -0.06
    erator
    -0.06
    curl
    -0.06
    det
    -0.06
     chế
    -0.06
     trips
    -0.06
    isto
    -0.06
    POSITIVE LOGITS
     listBox
    0.06
     appare
    0.06
    .Quad
    0.06
     yüksek
    0.06
    ultural
    0.06
    _phase
    0.06
    @Enable
    0.06
    -yyyy
    0.06
     Dynamics
    0.06
     outlined
    0.06
    Act Density 0.039%

    No Known Activations