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

    Neuronpedia

    INDEX
    Explanations

    Titles and headers

    np_max-act · gemini-2.0-flash

    statistical properties and patterns within multifractal data.

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

    The neuron activates on numeric tokens—especially floating‐point and decimal numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .DataGridViewAutoSize
    -0.07
     IDisposable
    -0.07
    'am
    -0.06
    .ef
    -0.06
    ojení
    -0.06
    iêu
    -0.06
     Karn
    -0.06
     Harm
    -0.06
    inus
    -0.06
     lui
    -0.06
    POSITIVE LOGITS
    osomal
    0.07
    social
    0.06
    >\↵
    0.06
     Adult
    0.06
    aseline
    0.06
    acier
    0.06
     down
    0.06
    سة
    0.06
    [selected
    0.06
     Ple
    0.06
    Act Density 0.006%

    No Known Activations