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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frontier
    -0.07
    ivered
    -0.07
     Solomon
    -0.07
    elapsed
    -0.07
    blocked
    -0.07
     traveler
    -0.07
     False
    -0.07
    Quit
    -0.07
    ٫
    -0.07
     hunting
    -0.07
    POSITIVE LOGITS
    .SQLException
    0.06
     Sadece
    0.06
     صرف
    0.06
     Tiles
    0.06
    ній
    0.06
    При
    0.06
     detrimental
    0.06
    .Exchange
    0.06
     teslim
    0.06
    짝
    0.06
    Act Density 0.051%

    No Known Activations