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

    Neuronpedia

    INDEX
    Explanations

    advertisements

    np_max-act · gemini-2.0-flash

    The neuron fires on the first significant content word at the start of a new sentence (i.e. it marks sentence beginnings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    摇
    -0.07
     п
    -0.07
    測
    -0.06
    pled
    -0.06
    増
    -0.06
    rowser
    -0.06
    -outline
    -0.06
    �
    -0.06
    gulp
    -0.06
    іту
    -0.06
    POSITIVE LOGITS
     Careers
    0.07
    acea
    0.07
     Stuart
    0.06
     RELATED
    0.06
    Pers
    0.06
     lovely
    0.06
     legis
    0.06
     Dr
    0.06
     LIS
    0.06
    )';↵
    0.06
    Act Density 0.017%

    No Known Activations