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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash

    This neuron activates on code‐like syntax (e.g. programming keywords, punctuation, and structure).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Removal
    -0.07
    _boundary
    -0.07
    iox
    -0.07
    Bay
    -0.06
     giảng
    -0.06
     Similar
    -0.06
     Vid
    -0.06
     校
    -0.06
     Malone
    -0.06
     removal
    -0.06
    POSITIVE LOGITS
     �
    0.07
    (bits
    0.06
     yapacak
    0.06
    Δεν
    0.06
     طريق
    0.06
     실시
    0.06
     lob
    0.06
    ทำงาน
    0.06
    πλ
    0.06
    #![
    0.06
    Act Density 0.018%

    No Known Activations