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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash

    The neuron fires on C/C++ type‐declaration keywords (e.g. “class” or “struct”) indicating the start of a type definition.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    enschaft
    -0.07
    YPE
    -0.06
    θρώ
    -0.06
    -',
    -0.06
     rings
    -0.06
    LD
    -0.06
     Runnable
    -0.06
     ambassador
    -0.06
    네
    -0.06
    .ast
    -0.06
    POSITIVE LOGITS
     speeds
    0.07
     surrounds
    0.06
     quicker
    0.06
     anatom
    0.06
    (metadata
    0.06
     dimension
    0.06
    Adjusted
    0.06
     recruiting
    0.06
    оч
    0.06
    (ed
    0.06
    Act Density 0.002%

    No Known Activations