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

    Neuronpedia

    INDEX
    Explanations

    provided

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bear
    -0.07
    BLEM
    -0.06
    _exchange
    -0.06
     rock
    -0.06
    しゃ
    -0.06
     jumping
    -0.06
     recognize
    -0.06
     »
    -0.06
     Seat
    -0.06
    resents
    -0.06
    POSITIVE LOGITS
     Oliver
    0.09
    provided
    0.08
    ‐
    0.08
    D
    0.08
     pesso
    0.08
    (def
    0.08
    .D
    0.08
     product
    0.07
    fred
    0.07
     ND
    0.07
    Act Density 0.023%

    No Known Activations