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

    Neuronpedia

    INDEX
    Explanations

    does not occur

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    0.97
    ený
    0.90
    lockSeconds
    0.85
     stronę
    0.84
     smoked
    0.83
    िड
    0.80
     quits
    0.80
     kró
    0.79
     zvlá
    0.79
     gris
    0.79
    POSITIVE LOGITS
    ления
    0.84
    あらゆる
    0.79
     terjadinya
    0.76
    ✋
    0.75
    \/}
    0.71
    ✓
    0.71
     Nakon
    0.69
    kta
    0.69
    ktions
    0.69
    менно
    0.68
    Act Density 0.007%

    No Known Activations