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

    Neuronpedia

    INDEX
    Explanations

    well

    np_max-act · gemini-2.0-flash

    historical figures and significant events related to monarchy.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on positive, subjective evaluative adjectives (e.g. “compelling,” “interesting,” “riveting”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ensed
    -0.06
    端
    -0.06
    üyor
    -0.06
    .Virtual
    -0.06
     bikini
    -0.06
     keypad
    -0.06
     UT
    -0.06
     GW
    -0.06
    _ROM
    -0.06
    ';↵↵↵
    -0.06
    POSITIVE LOGITS
    ster
    0.06
    令人
    0.06
     ألف
    0.06
    第四
    0.06
    ۱۹۹
    0.06
    adia
    0.06
     Processor
    0.06
    股东
    0.06
    -delay
    0.06
     ihrer
    0.06
    Act Density 0.164%

    No Known Activations