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

    Neuronpedia

    INDEX
    Explanations

    psychic readings

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of requesting or providing personal details—especially names and dates of birth.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     hm
    -0.07
    ["@
    -0.06
    .ReadLine
    -0.06
     aby
    -0.06
    Wenn
    -0.06
    >-->↵
    -0.06
    anye
    -0.06
     jclass
    -0.06
    -s
    -0.06
    Чтобы
    -0.06
    POSITIVE LOGITS
     ngừng
    0.07
    ню
    0.07
    нений
    0.06
     Gold
    0.06
     NUITKA
    0.06
    employed
    0.06
    -toggle
    0.06
    gold
    0.06
     entrenched
    0.06
     سود
    0.06
    Act Density 0.018%

    No Known Activations