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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash

    This neuron fires on Ruby instance‐variable references (tokens like “@post”) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ้าช
    -0.07
     سر
    -0.07
    etype
    -0.06
    joint
    -0.06
    .ba
    -0.06
    .marker
    -0.06
     thanh
    -0.06
     Cleaning
    -0.06
     Become
    -0.06
     كن
    -0.06
    POSITIVE LOGITS
    langle
    0.07
    CALE
    0.06
     філь
    0.06
    IZES
    0.06
     법
    0.06
    gorithm
    0.06
     Decimal
    0.06
     товарів
    0.06
     мног
    0.06
    ють
    0.06
    Act Density 0.020%

    No Known Activations