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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المتح
    -0.08
     Math
    -0.07
    .opens
    -0.07
    烬
    -0.07
    .webkit
    -0.07
     Thumbnail
    -0.07
     Thief
    -0.07
    redential
    -0.07
    _ctl
    -0.07
    Required
    -0.06
    POSITIVE LOGITS
    }//
    0.07
    uminium
    0.07
     works
    0.07
    RODUCTION
    0.07
    Integral
    0.07
    increment
    0.07
    amination
    0.06
    Ol
    0.06
    尢
    0.06
    Dou
    0.06
    Act Density 0.154%

    No Known Activations