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

    Neuronpedia

    INDEX
    Explanations

    API endpoints/web requests

    np_max-act · gemini-2.0-flash

    This neuron spots leading indentation (the whitespace at the start of code lines).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    іла
    -0.07
     Zwe
    -0.07
     toned
    -0.06
    мат
    -0.06
     مس
    -0.06
     gode
    -0.06
     конкур
    -0.06
     Romantic
    -0.05
    Pane
    -0.05
     يم
    -0.05
    POSITIVE LOGITS
    Ư
    0.07
     chaired
    0.07
    (details
    0.06
    Obama
    0.06
     shortcode
    0.06
    responsive
    0.06
    "She
    0.06
     native
    0.06
     editor
    0.06
     getList
    0.06
    Act Density 0.009%

    No Known Activations