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

    Neuronpedia

    INDEX
    Explanations

    Vue templates

    np_max-act · gemini-2.0-flash

    The neuron activates on sequences of leading whitespace (indentation) before tags or code lines.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    opic
    -0.07
     Positioned
    -0.06
    \'
    -0.06
     Billboard
    -0.06
    nit
    -0.06
    _python
    -0.06
     orc
    -0.06
    ioxide
    -0.06
    Procedure
    -0.06
    命周期
    -0.06
    POSITIVE LOGITS
    (del
    0.07
     自动生成
    0.07
    ียงใหม
    0.06
    "/></
    0.06
     DevComponents
    0.06
     uç
    0.06
    0.06
     Jog
    0.06
     масс
    0.06
    >Edit
    0.06
    Act Density 0.012%

    No Known Activations