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

    Neuronpedia

    INDEX
    Explanations

    watching events unfold with emotion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    шлось
    0.74
     memperoleh
    0.72
    حصل
    0.69
     mengadakan
    0.69
    基づ
    0.68
    riek
    0.67
     الموجود
    0.66
     사항
    0.66
     получите
    0.66
    Selain
    0.66
    POSITIVE LOGITS
     helplessly
    1.43
     Netflix
    0.93
     intently
    0.85
     glass
    0.82
     horrified
    0.81
     helpless
    0.78
     fascinated
    0.77
     mesmer
    0.76
     embers
    0.73
     dalla
    0.73
    Act Density 0.005%

    No Known Activations