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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literals (constants) used to specify timing or delay values in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bidi
    -0.06
     presup
    -0.06
     beneficiaries
    -0.06
     disob
    -0.06
    (fabs
    -0.06
     commander
    -0.06
    »،
    -0.06
    _of
    -0.06
    _Application
    -0.06
     nk
    -0.06
    POSITIVE LOGITS
    MV
    0.07
     Nhật
    0.07
    ρίας
    0.07
    €
    0.07
     Brittany
    0.06
     SINGLE
    0.06
    MX
    0.06
     индивиду
    0.06
    ามารถ
    0.06
    _create
    0.06
    Act Density 0.041%

    No Known Activations