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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens and mathematical expressions (i.e., sequences of digits and formula‐style notation).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     HIS
    -0.07
     скор
    -0.06
     Bahamas
    -0.06
     系
    -0.06
    rection
    -0.06
    NOWLED
    -0.06
     Yunan
    -0.06
    (elements
    -0.06
     челов
    -0.06
     whats
    -0.06
    POSITIVE LOGITS
    Tbl
    0.07
    名
    0.06
     산업
    0.06
    DEFINED
    0.06
    bn
    0.06
    алась
    0.06
    .tb
    0.06
     delighted
    0.06
     iş
    0.06
     filib
    0.06
    Act Density 0.008%

    No Known Activations