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

    Neuronpedia

    INDEX
    Explanations

    life

    np_max-act · gemini-2.0-flash

    This neuron detects the phrase “quality of life.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     DEF
    -0.07
     ful
    -0.07
    IBUT
    -0.06
    "is
    -0.06
     Subset
    -0.06
    _MetaData
    -0.06
     tet
    -0.06
     fur
    -0.06
    _COMPAT
    -0.06
    .UtcNow
    -0.06
    POSITIVE LOGITS
    klär
    0.07
    */
↵
    0.07
    bage
    0.07
     громадян
    0.07
    就是
    0.06
     ใน
    0.06
     toughness
    0.06
    ければ
    0.06
     enquanto
    0.06
    lias
    0.06
    Act Density 0.009%

    No Known Activations