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

    Neuronpedia

    INDEX
    Explanations

    Positive emotions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estos
    -0.06
     Dez
    -0.06
    许多
    -0.06
    务工
    -0.06
     FVector
    -0.06
     Fiji
    -0.06
    苁
    -0.06
     dazu
    -0.06
    战争
    -0.06
     lc
    -0.06
    POSITIVE LOGITS
    த
    0.08
    -be
    0.07
     Greek
    0.06
    迷
    0.06
    _PA
    0.06
    瀑
    0.06
    ODY
    0.06
     extraordinary
    0.06
    מית
    0.06
    пут
    0.06
    Act Density 0.196%

    No Known Activations