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

    Neuronpedia

    INDEX
    Explanations

    Special characters

    np_max-act · gemini-2.0-flash

    This neuron activates on author and affiliation metadata (names, email/URLs, institutional info) rather than the main body text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    alone
    -0.07
     Owl
    -0.06
     collapsed
    -0.06
    StackTrace
    -0.06
    �
    -0.06
     turbines
    -0.06
    HD
    -0.06
     standalone
    -0.06
     schl
    -0.06
     hen
    -0.06
    POSITIVE LOGITS
    ратить
    0.07
    сутств
    0.07
    axios
    0.07
    樓
    0.06
     بهبود
    0.06
    ϊκ
    0.06
     Федерации
    0.06
     deductions
    0.06
    \Response
    0.06
    (ALOAD
    0.06
    Act Density 0.014%

    No Known Activations