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

    Neuronpedia

    INDEX
    Explanations

    former

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vys
    -0.07
    lasting
    -0.07
    -score
    -0.06
    NO
    -0.06
     circum
    -0.06
    .Add
    -0.06
    _day
    -0.06
     bows
    -0.06
     pertaining
    -0.06
    .it
    -0.06
    POSITIVE LOGITS
     genres
    0.07
    ΙΟ
    0.06
     geçir
    0.06
    itchens
    0.06
     onNext
    0.06
     če
    0.06
     (?)
    0.06
     해외
    0.06
    .genre
    0.06
    CodeGen
    0.06
    Act Density 0.016%

    No Known Activations