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

    Neuronpedia

    INDEX
    Explanations

    differentiable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ef
    -0.07
    评论
    -0.07
     appending
    -0.06
     DX
    -0.06
     ['
    -0.06
    ný
    -0.06
     POW
    -0.06
    apult
    -0.06
     Jud
    -0.06
    ajs
    -0.06
    POSITIVE LOGITS
     identifiable
    0.07
    /cal
    0.07
    ----------</
    0.07
    ющие
    0.07
    NORMAL
    0.07
    (Initialized
    0.07
     reduced
    0.07
     Higher
    0.06
     dị
    0.06
    textAlign
    0.06
    Act Density 0.005%

    No Known Activations