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

    Neuronpedia

    INDEX
    Explanations

    California

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grin
    -0.07
    ниць
    -0.06
     benches
    -0.06
    神
    -0.06
     docking
    -0.06
    OURSE
    -0.06
     hull
    -0.06
     pot
    -0.06
     jitter
    -0.06
    Failure
    -0.06
    POSITIVE LOGITS
     California
    0.11
    California
    0.09
     Calif
    0.09
     Californ
    0.08
    .Subject
    0.07
     spectator
    0.07
    WM
    0.06
    кат
    0.06
    .parseFloat
    0.06
    hyth
    0.06
    Act Density 0.009%

    No Known Activations