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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric tokens (especially decimal numbers) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lanc
    -0.06
     preparing
    -0.06
     =================================================================================
    -0.06
     partido
    -0.06
     recurs
    -0.06
    antas
    -0.06
     Το
    -0.06
     постанов
    -0.05
    Artifact
    -0.05
    户
    -0.05
    POSITIVE LOGITS
     Dairy
    0.07
     Courtney
    0.07
     Α
    0.06
     WebGL
    0.06
     protagon
    0.06
     cooker
    0.06
    ';
↵
    0.06
    DATED
    0.06
    Architecture
    0.06
     McC
    0.06
    Act Density 0.004%

    No Known Activations