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

    Neuronpedia

    INDEX
    Explanations

    Name

    np_max-act · gemini-2.0-flash

    The neuron activates on XML attribute names (e.g. “BuildableName,” “BlueprintName,” “Identifier”) in Xcode scheme files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Amt
    -0.07
    _helpers
    -0.07
    BUY
    -0.07
    'article
    -0.07
    cce
    -0.07
    货
    -0.07
    だ
    -0.07
    Surface
    -0.07
    efficient
    -0.07
     reservations
    -0.07
    POSITIVE LOGITS
    \\/
    0.06
     resisting
    0.06
     перек
    0.06
    ันด
    0.06
    _er
    0.06
    .Conv
    0.06
    ／↵
    0.06
    _SR
    0.06
     ann
    0.06
    ););↵
    0.06
    Act Density 0.014%

    No Known Activations