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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash

    The neuron is specialized in spotting code fragments and programming‐related tokens (e.g. identifiers, operators, and punctuation) within a text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    employ
    -0.07
    (album
    -0.07
    .Home
    -0.06
    NEY
    -0.06
     JWT
    -0.06
     decimals
    -0.06
    Management
    -0.06
    ert
    -0.06
    iators
    -0.06
     key
    -0.06
    POSITIVE LOGITS
     každé
    0.07
     deflect
    0.07
    <>(
    0.07
     centerY
    0.06
     Ayrıca
    0.06
    .isNullOrEmpty
    0.06
     Також
    0.06
     пів
    0.06
     UnityEngine
    0.06
     quelques
    0.06
    Act Density 0.075%

    No Known Activations