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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indrukwekk
    -0.08
     disproportionately
    -0.08
     ciddi
    -0.08
     امر
    -0.08
    Oval
    -0.08
    开启
    -0.07
    ()↵↵↵↵
    -0.07
     مطالب
    -0.07
     disproportion
    -0.07
     impregn
    -0.07
    POSITIVE LOGITS
     simpler
    0.12
     shorter
    0.09
    asier
    0.09
     weaker
    0.09
    Explicit
    0.09
     lieber
    0.08
     stärker
    0.08
     kerül
    0.08
     explicit
    0.08
     сух
    0.08
    Act Density 0.030%

    No Known Activations