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

    Neuronpedia

    INDEX
    Explanations

    Positions of authority

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     постав
    -0.07
    агато
    -0.07
     unbearable
    -0.06
     창
    -0.06
     retrospect
    -0.06
     testimon
    -0.06
    usterity
    -0.06
    coe
    -0.06
     Pow
    -0.06
    -n
    -0.06
    POSITIVE LOGITS
     Alt
    0.07
    .Repositories
    0.07
    지
    0.06
     Jennings
    0.06
     Buy
    0.06
    .lot
    0.06
    ortho
    0.06
     buyers
    0.06
    ($('.
    0.06
    )&&
    0.06
    Act Density 0.187%

    No Known Activations