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

    Neuronpedia

    INDEX
    Explanations

    video games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mafia
    -0.07
    薦
    -0.07
    ΙΣ
    -0.07
     Aboriginal
    -0.07
    _more
    -0.07
     maken
    -0.06
     xảy
    -0.06
    �
    -0.06
     yelled
    -0.06
    Ice
    -0.06
    POSITIVE LOGITS
     culpa
    0.06
     Parts
    0.06
    _Run
    0.06
     cryptography
    0.06
    Hey
    0.06
    메
    0.06
    LatLng
    0.06
    ßer
    0.05
    (withId
    0.05
     tvá
    0.05
    Act Density 0.009%

    No Known Activations