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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guards
    -0.07
    holder
    -0.06
     сосед
    -0.06
     Brooke
    -0.06
     Edison
    -0.06
    Sit
    -0.06
    PushButton
    -0.06
     Reeves
    -0.06
    .assertIs
    -0.06
     compressor
    -0.06
    POSITIVE LOGITS
    익
    0.06
    implicit
    0.06
    ック
    0.06
    ocurrency
    0.06
    лика
    0.06
    (phi
    0.06
    онів
    0.06
    phia
    0.06
    HEST
    0.06
     visible
    0.06
    Act Density 0.011%

    No Known Activations