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

    Neuronpedia

    INDEX
    Explanations

    .In

    np_max-act · gemini-2.0-flash

    The neuron is tuned to spot floating‐point number literals (decimal constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (month
    -0.07
    _mail
    -0.07
    kj
    -0.07
     Spend
    -0.06
    .getValue
    -0.06
     MX
    -0.06
     Fra
    -0.06
     نیز
    -0.06
    ذا
    -0.06
     بح
    -0.06
    POSITIVE LOGITS
     mattered
    0.07
     öldür
    0.06
    nection
    0.06
    usable
    0.06
     Bitcoin
    0.06
     �
    0.06
    няет
    0.06
    ाहन
    0.06
    ATUS
    0.06
     embar
    0.06
    Act Density 0.004%

    No Known Activations