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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric version or kernel‐version constants (i.e. version numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ated
    -0.07
     Lớp
    -0.06
    _adc
    -0.06
    430
    -0.06
    ktop
    -0.06
     bitir
    -0.06
    蘇
    -0.06
     وفق
    -0.06
    .quantity
    -0.06
    RenderWindow
    -0.06
    POSITIVE LOGITS
    ingle
    0.07
     Α
    0.07
     disruptions
    0.06
    just
    0.06
     Scalar
    0.06
    confidence
    0.06
    Description
    0.06
     sme
    0.06
    ुध
    0.06
     fines
    0.06
    Act Density 0.004%

    No Known Activations