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

    Neuronpedia

    INDEX
    Explanations

    ades

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     a
    -0.09
     their
    -0.08
     An
    -0.08
     A
    -0.08
     an
    -0.08
     the
    -0.08
     The
    -0.07
    methods
    -0.07
     Their
    -0.07
     his
    -0.07
    POSITIVE LOGITS
     وفي
    0.07
    _FOLLOW
    0.06
     ostream
    0.06
     внут
    0.06
     eben
    0.06
    .Xna
    0.06
    "](
    0.06
     "</
    0.06
    benhavn
    0.06
     вполне
    0.06
    Act Density 0.197%

    No Known Activations