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

    Neuronpedia

    INDEX
    Explanations

    Hyphen

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect arithmetic expressions or instructions (e.g. words like “divide,” “calculate,” “times,” “minus,” etc., together with numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     urges
    -0.08
     easiest
    -0.07
     budgets
    -0.06
     IRS
    -0.06
     synchronization
    -0.06
    .crop
    -0.06
    .result
    -0.06
    .CLASS
    -0.06
     learn
    -0.06
    33
    -0.06
    POSITIVE LOGITS
    \Events
    0.07
    _inp
    0.07
    orgot
    0.07
    ’da
    0.07
     quốc
    0.07
     Civil
    0.07
    ่ก
    0.07
     →↵↵
    0.07
    Correo
    0.07
    чення
    0.07
    Act Density 0.021%

    No Known Activations