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

    Neuronpedia

    INDEX
    Explanations

    alpha and beta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ở
    -0.07
     freopen
    -0.07
     ND
    -0.07
     с
    -0.07
     در
    -0.06
    LoggedIn
    -0.06
     پیشینه
    -0.06
    N
    -0.06
    IFn
    -0.06
    ایج
    -0.06
    POSITIVE LOGITS
    	alpha
    0.08
     beta
    0.08
    ogra
    0.08
     gamma
    0.07
     sweet
    0.07
     batter
    0.07
    ifacts
    0.07
     district
    0.07
     alpha
    0.07
     rebel
    0.07
    Act Density 0.013%

    No Known Activations