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

    Neuronpedia

    INDEX
    Explanations

    schools

    np_max-act · gemini-2.0-flash

    The neuron fires on capitalized named entities—e.g. institutions, departments, schools, places, people’s titles—essentially spotting proper names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    elements related to personal growth and self-improvement.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tìm
    -0.06
     follow
    -0.06
    _HP
    -0.06
    ,b
    -0.06
    (b
    -0.05
    YPD
    -0.05
    plings
    -0.05
    lays
    -0.05
     apparel
    -0.05
     individually
    -0.05
    POSITIVE LOGITS
     تیر
    0.07
    ･･
    0.07
    řet
    0.07
     dět
    0.07
    ủng
    0.07
     nejsou
    0.07
    ━�
    0.07
    ット
    0.07
    ीवन
    0.06
     Да
    0.06
    Act Density 0.145%

    No Known Activations