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

    Neuronpedia

    INDEX
    Explanations

    patent/scientific writing

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens and decimal numbers (e.g. patent numbers and number fragments).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .P
    -0.07
    sv
    -0.07
     hug
    -0.07
    -order
    -0.07
    rál
    -0.07
     Ages
    -0.06
     Importance
    -0.06
     XII
    -0.06
    HL
    -0.06
    ैश
    -0.06
    POSITIVE LOGITS
     jednot
    0.07
     contend
    0.06
     Align
    0.06
    SQLException
    0.06
     학생
    0.06
     changing
    0.06
     skup
    0.06
     Changing
    0.06
     было
    0.06
    ittance
    0.06
    Act Density 0.037%

    No Known Activations