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

    Neuronpedia

    INDEX
    Explanations

    News articles/blog posts

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting floating-point number tokens (decimal numerals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    imbledon
    -0.06
    _SHADOW
    -0.06
    (_('
    -0.06
    กฎหมาย
    -0.06
    _hierarchy
    -0.06
    Grammar
    -0.06
     kum
    -0.06
    riba
    -0.06
    	base
    -0.06
    .fin
    -0.06
    POSITIVE LOGITS
    velt
    0.07
     cả
    0.07
    idan
    0.07
    「そう
    0.07
     desserts
    0.06
    よび
    0.06
     pci
    0.06
     wollen
    0.06
    veis
    0.06
    τής
    0.06
    Act Density 0.245%

    No Known Activations