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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    np_max-act · gemini-2.0-flash

    the neuron detects parts of alphanumeric product model identifiers (e.g. tokens in model numbers combining letters and digits).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Forest
    -0.07
    _drv
    -0.07
    _da
    -0.07
    p
    -0.06
     Milan
    -0.06
    ую
    -0.06
    Detector
    -0.06
    (Field
    -0.06
     Janet
    -0.06
    ۱
    -0.06
    POSITIVE LOGITS
     于
    0.07
     الأمريكي
    0.07
     الات
    0.07
     dific
    0.07
     sponsor
    0.07
     publishes
    0.07
     평
    0.07
    ﾆﾆﾆﾆ
    0.06
     afirm
    0.06
    .Throws
    0.06
    Act Density 0.037%

    No Known Activations