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

    Neuronpedia

    INDEX
    Explanations

    10

    np_max-act · gemini-2.0-flash

    This neuron activates on list item numbers (the numeric markers at the start of enumerated entries).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    004
    -0.07
     زیست
    -0.07
     saison
    -0.07
     candid
    -0.06
    Grupo
    -0.06
     Realty
    -0.06
    .Cancel
    -0.06
     να
    -0.06
     Hizmet
    -0.06
    _variant
    -0.06
    POSITIVE LOGITS
    etooth
    0.07
    aaa
    0.06
    mé
    0.06
    STANCE
    0.06
    shops
    0.06
    ΕΤ
    0.06
    十一
    0.06
     τε
    0.06
    ­n
    0.06
    mites
    0.06
    Act Density 0.018%

    No Known Activations