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

    Neuronpedia

    INDEX
    Explanations

    R

    np_max-act · gemini-2.0-flash

    This neuron detects tokens naming and numbering variable substituents in chemical formulas (e.g. R1, R2, numeric locants).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sponsorship
    -0.06
    ‌کن
    -0.06
     dues
    -0.06
    .ONE
    -0.06
    owski
    -0.06
    _fd
    -0.06
    STAT
    -0.06
     NU
    -0.06
     phosphate
    -0.06
     jaar
    -0.06
    POSITIVE LOGITS
    imetype
    0.07
    xpath
    0.07
    350
    0.07
    365
    0.07
     Cay
    0.06
    :inline
    0.06
    nullable
    0.06
    (gcf
    0.06
    _runs
    0.06
    ically
    0.06
    Act Density 0.002%

    No Known Activations