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

    Neuronpedia

    INDEX
    Explanations

    Action items and future tense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     klasik
    -0.10
     fortuna
    -0.09
     防
    -0.09
     atrações
    -0.09
    czy
    -0.08
    emory
    -0.08
    Spend
    -0.08
     защиты
    -0.08
     o't
    -0.08
     популяр
    -0.08
    POSITIVE LOGITS
     deadlines
    0.10
     Assigned
    0.10
    ว่าจะ
    0.10
    将在
    0.09
    期限
    0.09
     deadline
    0.09
    Assigned
    0.09
     plazo
    0.09
    Immediate
    0.09
    .Callback
    0.09
    Act Density 0.050%

    No Known Activations