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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (years, dates, percentages, and other numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    AV
    -0.07
    19
    -0.07
    15
    -0.07
    xDC
    -0.07
    23
    -0.07
    98
    -0.07
     Aid
    -0.07
    at
    -0.07
    At
    -0.06
    extent
    -0.06
    POSITIVE LOGITS
     the
    0.13
     on
    0.10
    -the
    0.10
     The
    0.10
     THE
    0.09
     its
    0.09
    The
    0.09
     my
    0.09
    the
    0.08
     his
    0.08
    Act Density 0.113%

    No Known Activations