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

    Neuronpedia

    INDEX
    Explanations

    percentages

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect numeric quantitative expressions (counts, percentages, rates) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _factor
    -0.06
     Honor
    -0.06
     Apprentice
    -0.06
    .Build
    -0.06
     gens
    -0.06
    .rep
    -0.06
    ать
    -0.06
    Immediate
    -0.06
    _endpoint
    -0.06
    .sk
    -0.06
    POSITIVE LOGITS
     propositions
    0.07
     \`
    0.06
    _PRI
    0.06
     nejd
    0.06
     inferior
    0.06
     canActivate
    0.06
     newData
    0.06
    ».
    0.06
     ماي
    0.06
     unfavor
    0.06
    Act Density 0.028%

    No Known Activations