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
    .Seek
    -0.08
     silhouette
    -0.07
    Guard
    -0.07
     Reve
    -0.07
    _ORIENTATION
    -0.07
    _DEPEND
    -0.07
    &lt
    -0.06
     woven
    -0.06
    gold
    -0.06
     backward
    -0.06
    POSITIVE LOGITS
    intval
    0.07
     العاص
    0.07
     đặc
    0.07
    דות
    0.07
     '');↵
    0.07
    дан
    0.07
    خص
    0.07
    精彩
    0.07
    fav
    0.06
    捧
    0.06
    Act Density 0.006%

    No Known Activations