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

    Neuronpedia

    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash

    requests for programming tasks related to network and light automation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects decimal numeric tokens (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     asshole
    -0.06
    路径
    -0.06
    ศาสตร
    -0.06
    окол
    -0.06
     Sandwich
    -0.06
     boutique
    -0.06
    Hy
    -0.06
     values
    -0.06
     package
    -0.06
     strongest
    -0.06
    POSITIVE LOGITS
     Tipo
    0.07
    (dataSource
    0.07
    _elim
    0.07
    FAILURE
    0.07
    ž
    0.06
    portal
    0.06
    يلم
    0.06
    ifton
    0.06
    ESPN
    0.06
     Whe
    0.06
    Act Density 0.041%

    No Known Activations