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

    Neuronpedia

    INDEX
    Explanations

    agreement and readiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     worried
    0.91
    iglas
    0.85
    了好
    0.80
     hilfre
    0.80
     worries
    0.80
     blobs
    0.80
    嘛
    0.79
     важ
    0.77
     your
    0.77
     lucky
    0.77
    POSITIVE LOGITS
     Agreement
    1.08
     Deal
    1.01
    Agreement
    1.00
     রাজি
    1.00
     agreement
    0.92
     deal
    0.87
    约定
    0.87
     agrees
    0.86
     Ready
    0.85
     agree
    0.85
    Act Density 0.244%

    No Known Activations