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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on numeric literals (especially decimal/fractional numbers) in mathematical or technical contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     numberOfRows
    -0.07
    -ra
    -0.07
    iptables
    -0.07
    amphetamine
    -0.06
     Clar
    -0.06
     Walters
    -0.06
    ]["
    -0.06
     blush
    -0.06
    ระหว
    -0.06
     Provid
    -0.06
    POSITIVE LOGITS
     dedi
    0.06
    Bloc
    0.06
    ерт
    0.06
    )(↵
    0.06
     дви
    0.06
     DESC
    0.06
    ESCO
    0.06
    umen
    0.06
     irreversible
    0.06
     انقل
    0.06
    Act Density 0.009%

    No Known Activations