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

    Neuronpedia

    INDEX
    Explanations

    AC/Class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fade
    -0.09
     đạo
    -0.08
    ילות
    -0.08
     datt
    -0.08
    versa
    -0.07
     распространя
    -0.07
     uplifting
    -0.07
     premières
    -0.07
     Bool
    -0.07
     GPU
    -0.07
    POSITIVE LOGITS
     achievable
    0.08
     اللي
    0.07
    ollipop
    0.07
    sq
    0.07
     квад
    0.07
    Nossa
    0.07
    ific
    0.07
     reachable
    0.07
    razi
    0.07
     softball
    0.07
    Act Density 0.001%

    No Known Activations