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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron is looking for floating-point numeric values (decimal numbers), as they appear in coordinate lists.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sublic
    -0.07
    的に
    -0.07
    ^[
    -0.07
    Metadata
    -0.07
     helium
    -0.07
    _notice
    -0.06
    曰
    -0.06
     Дж
    -0.06
     Eq
    -0.06
    keiten
    -0.06
    POSITIVE LOGITS
     sponsors
    0.08
     sponsor
    0.08
    ',{'
    0.07
    (scanner
    0.06
     Croatian
    0.06
    ponsors
    0.06
    -defense
    0.06
    Oct
    0.06
     Mack
    0.06
     spons
    0.06
    Act Density 0.004%

    No Known Activations