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

    Neuronpedia

    INDEX
    Explanations

    Star Wars Force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fix
    -0.09
    targets
    -0.08
    fix
    -0.08
     Yemen
    -0.08
     tomatoes
    -0.08
    _fix
    -0.08
     Fix
    -0.08
     types
    -0.08
    Fix
    -0.08
     cooked
    -0.08
    POSITIVE LOGITS
    빛
    0.09
     fenómeno
    0.08
     phenomena
    0.08
     Jedi
    0.08
     trance
    0.08
    奉
    0.08
     phenomenon
    0.08
     phenomen
    0.08
    祝
    0.08
    ª
    0.08
    Act Density 0.001%

    No Known Activations