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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    This neuron primarily detects numeric literal tokens (i.e. standalone numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dass
    -0.07
    alled
    -0.07
     tedy
    -0.06
    IPHER
    -0.06
    'all
    -0.06
    iday
    -0.06
    _Parms
    -0.06
     dne
    -0.06
    uddenly
    -0.06
    avor
    -0.06
    POSITIVE LOGITS
    emics
    0.06
     entitled
    0.06
     ‎
    0.06
    Levels
    0.06
     Quebec
    0.06
    Uploaded
    0.06
    getName
    0.06
     exped
    0.06
    -_
    0.06
     نشان
    0.06
    Act Density 0.012%

    No Known Activations