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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    众生
    -0.08
    _activity
    -0.07
     tern
    -0.07
    AGMENT
    -0.07
    alent
    -0.07
    衅
    -0.07
    家族
    -0.07
     inclus
    -0.07
    uncture
    -0.07
    Dealer
    -0.07
    POSITIVE LOGITS
    elines
    0.07
    check
    0.07
    ном
    0.07
     math
    0.07
    化工
    0.06
    зем
    0.06
    thetic
    0.06
    .''↵↵
    0.06
    _checks
    0.06
    其他
    0.06
    Act Density 0.050%

    No Known Activations