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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    This neuron detects programming runtime notices, warnings, and deprecation messages (e.g., “Strict Standards:”, “Deprecated:”, “Warning:”) in code output.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Drawable
    -0.07
    株
    -0.07
     Producto
    -0.07
    -relative
    -0.06
    .BackgroundImageLayout
    -0.06
     thương
    -0.06
    (provider
    -0.06
    ออกแบบ
    -0.06
    れ
    -0.06
     Ecuador
    -0.06
    POSITIVE LOGITS
     testified
    0.07
    Deprecated
    0.06
     Soldier
    0.06
     assms
    0.06
     depletion
    0.06
     pledged
    0.06
     '"';↵
    0.06
     ніч
    0.06
     QPainter
    0.06
     seized
    0.06
    Act Density 0.002%

    No Known Activations