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

    Neuronpedia

    INDEX
    Explanations

    future capabilities and awareness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     좋은
    0.54
     малень
    0.50
     хороший
    0.48
     trochę
    0.47
     kolay
    0.46
     mici
    0.46
    ですので
    0.45
     banyak
    0.44
     довольно
    0.44
     excellent
    0.44
    POSITIVE LOGITS
     fractal
    0.53
    超越
    0.50
     perceiving
    0.49
    意识到
    0.48
     aware
    0.47
     comprehend
    0.46
     encompass
    0.46
     intuit
    0.46
     осозна
    0.46
     merging
    0.46
    Act Density 0.017%

    No Known Activations