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

    Neuronpedia

    INDEX
    Explanations

    I used to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nyaman
    0.78
     accett
    0.75
     gå
    0.73
     acept
    0.70
     bahagia
    0.68
     cheg
    0.68
     सहमति
    0.67
     extinguish
    0.67
     divent
    0.66
     diterima
    0.66
    POSITIVE LOGITS
    屶
    0.83
    বন্দর
    0.78
     যারা
    0.78
    ето
    0.74
     Montoya
    0.73
    cido
    0.73
     Tuttle
    0.72
    ulé
    0.72
     multipliers
    0.71
    tion
    0.71
    Act Density 0.026%

    No Known Activations