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

    Neuronpedia

    INDEX
    Explanations

    mirror neurons fire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     limitless
    0.69
     любит
    0.67
     loves
    0.63
     forgiving
    0.61
     scalable
    0.60
     infinite
    0.60
     forgets
    0.60
     love
    0.60
     беско
    0.59
     forgotten
    0.57
    POSITIVE LOGITS
     Selain
    0.90
     Enquanto
    0.90
     sowie
    0.89
    此外
    0.85
     nonché
    0.85
     ancien
    0.85
     valamint
    0.85
     Foi
    0.84
     dikutip
    0.84
     Namun
    0.84
    Act Density 0.010%

    No Known Activations