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

    Neuronpedia

    INDEX
    Explanations

    check

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     particular
    -0.10
    Mersi
    -0.09
    Namun
    -0.09
    Therefore
    -0.09
    [Math
    -0.09
    <|reserved_200013|>
    -0.09
    Moreover
    -0.09
    Teil
    -0.09
    มัคร
    -0.09
     էին
    -0.09
    POSITIVE LOGITS
     &
    0.10
     :
    0.10
     and
    0.09
     ::
    0.09
     questi
    0.08
     such
    0.08
     be
    0.08
     такие
    0.08
     такі
    0.08
     **
    0.08
    Act Density 0.093%

    No Known Activations