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

    Neuronpedia

    INDEX
    Explanations

    data types

    np_max-act · gemini-2.0-flash

    The neuron is specialized to detect mentions of “data types.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     triệu
    -0.07
    цем
    -0.07
     vegetation
    -0.07
     permitting
    -0.07
    occasion
    -0.07
     physique
    -0.07
     permits
    -0.07
     lore
    -0.06
     outcomes
    -0.06
     shielding
    -0.06
    POSITIVE LOGITS
    jav
    0.08
    atatype
    0.08
     DataType
    0.08
    (bt
    0.08
    .astype
    0.07
    creator
    0.07
     bytecode
    0.07
    _exist
    0.06
    _aes
    0.06
     DataTypes
    0.06
    Act Density 0.007%

    No Known Activations