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

    Neuronpedia

    INDEX
    Explanations

    human

    np_max-act · gemini-2.0-flash

    This neuron fires on Portuguese-language words or morphemes, effectively detecting segments written in Portuguese.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    hits
    -0.06
     But
    -0.06
     além
    -0.06
    umption
    -0.06
    Alright
    -0.06
    ounces
    -0.05
    ValueType
    -0.05
    _AMOUNT
    -0.05
     करत
    -0.05
     Duty
    -0.05
    POSITIVE LOGITS
     czy
    0.07
    east
    0.07
     arcpy
    0.07
    0.07
    Collector
    0.06
    ryan
    0.06
    ivy
    0.06
    /forms
    0.06
    .getMap
    0.06
    ίναι
    0.06
    Act Density 0.030%

    No Known Activations