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

    Neuronpedia

    INDEX
    Explanations

    continuity signal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पिला
    0.39
    ütt
    0.39
     जीते
    0.38
     fraternity
    0.38
    Una
    0.38
     укра
    0.38
    VICIO
    0.38
     製
    0.37
    त्व
    0.37
     incul
    0.37
    POSITIVE LOGITS
    िसिटी
    0.42
    يند
    0.39
     vend
    0.38
     soát
    0.36
    नल
    0.36
    次数
    0.36
     resalt
    0.36
    ेक्ट
    0.36
    yst
    0.36
    ontinuous
    0.36
    Act Density 0.000%

    No Known Activations