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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act · gemini-2.0-flash

    The neuron fires on parts of error‐reporting format strings, specifically the “%v” (percent‐v) formatting verb inside calls like fmt.Errorf.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    3
    -0.07
     Apartment
    -0.06
     Locale
    -0.06
    (station
    -0.06
     your
    -0.06
    .handleError
    -0.06
    (mac
    -0.06
    (material
    -0.06
    ğa
    -0.06
    uls
    -0.06
    POSITIVE LOGITS
    ゴリ
    0.07
    odings
    0.06
    claimed
    0.06
    native
    0.06
    .Round
    0.06
    -exclusive
    0.06
     isKindOfClass
    0.06
    Golden
    0.06
     ",");↵
    0.06
    dictionary
    0.06
    Act Density 0.004%

    No Known Activations