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

    Neuronpedia

    INDEX
    Explanations

    viewing content discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pedal
    0.89
     Kl
    0.88
     Nap
    0.86
     Briggs
    0.85
     بول
    0.83
     kl
    0.82
     музыкан
    0.81
     music
    0.81
     جنگ
    0.80
    Lil
    0.80
    POSITIVE LOGITS
     View
    2.58
    view
    2.51
    View
    2.48
     view
    2.37
     VIEW
    2.33
    VIEW
    2.28
     Views
    2.21
    views
    2.13
    Views
    2.12
     Viewing
    2.00
    Act Density 0.223%

    No Known Activations