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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron is triggered by numeric reference identifiers (the three- or four-digit numbers in bracketed citation keys).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Evangel
    -0.07
     Effect
    -0.07
     vypl
    -0.07
     needy
    -0.07
    coop
    -0.07
     Explore
    -0.06
    Nut
    -0.06
    Cette
    -0.06
    Sparse
    -0.06
    outlined
    -0.06
    POSITIVE LOGITS
     homeschool
    0.06
    ('$
    0.06
    ,(
    0.06
    専
    0.06
     Nelson
    0.06
    ��
    0.06
    ========
    0.06
    faction
    0.06
     $↵
    0.06
     ┃
    0.06
    Act Density 0.003%

    No Known Activations