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

    Neuronpedia

    INDEX
    Explanations

    base to con

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     based
    0.75
     outside
    0.70
     similarly
    0.67
     constructs
    0.67
    ব
    0.67
     engages
    0.65
    ສາ
    0.65
    ুৎ
    0.65
     signaled
    0.65
    ॉन
    0.64
    POSITIVE LOGITS
     yang
    1.01
     dell
    0.95
    ในการ
    0.91
     nell
    0.90
    ที่ไม่
    0.89
    ที่
    0.88
     untuk
    0.84
     những
    0.84
     nella
    0.81
     並
    0.81
    Act Density 0.307%

    No Known Activations