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

    Neuronpedia

    INDEX
    Explanations

    jokes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Swords
    -0.07
    _square
    -0.06
    │
    -0.06
     aday
    -0.06
    -0.06
     unintention
    -0.06
     Thornton
    -0.05
     Jacques
    -0.05
    .creation
    -0.05
     shrink
    -0.05
    POSITIVE LOGITS
    rolley
    0.07
     replied
    0.07
     pushing
    0.06
     electr
    0.06
    NotFoundError
    0.06
     (;;
    0.06
    Genre
    0.06
     Scar
    0.06
    ComputedStyle
    0.06
    acje
    0.06
    Act Density 0.194%

    No Known Activations