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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    985
    -0.07
     lofty
    -0.07
    (com
    -0.06
     polož
    -0.06
    ，从
    -0.06
     tantal
    -0.06
     game
    -0.06
     Kirk
    -0.06
    -0.06
     Situation
    -0.06
    POSITIVE LOGITS
     fluor
    0.07
     Klan
    0.07
    vet
    0.06
     MPC
    0.06
     expiry
    0.06
    ニック
    0.06
     Hers
    0.06
    .TABLE
    0.06
     estão
    0.06
    alo
    0.06
    Act Density 0.000%

    No Known Activations