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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron detects numeric literals in code (especially version‐check numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -span
    -0.07
     单
    -0.07
    之间
    -0.07
     ارتباط
    -0.06
    学习
    -0.06
    _acc
    -0.06
    ">&
    -0.06
     subsequ
    -0.06
    animations
    -0.06
    '].'/
    -0.06
    POSITIVE LOGITS
    .twitter
    0.06
     ویژه
    0.06
     Αθή
    0.06
     Butterfly
    0.06
    してる
    0.06
     국가
    0.06
    moth
    0.06
     využí
    0.06
     inquire
    0.06
    χεδόν
    0.05
    Act Density 0.021%

    No Known Activations