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

    Neuronpedia

    INDEX
    Explanations

    board

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mix
    -0.07
     elections
    -0.07
    !=
    -0.06
     fans
    -0.06
    .res
    -0.06
    _velocity
    -0.06
     citizens
    -0.06
     news
    -0.06
     dum
    -0.06
     rainfall
    -0.06
    POSITIVE LOGITS
     skateboard
    0.08
     boarding
    0.07
    board
    0.07
    boards
    0.07
     Binder
    0.07
    boarding
    0.07
    AllowAnonymous
    0.07
     Ninth
    0.06
    atically
    0.06
     respectfully
    0.06
    Act Density 0.001%

    No Known Activations