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
    ,^
    -0.09
     spectacle
    -0.08
     مذه
    -0.08
    -esque
    -0.08
     piston
    -0.08
    stätten
    -0.08
    vors
    -0.08
     henkil
    -0.08
     clickable
    -0.07
     فلس
    -0.07
    POSITIVE LOGITS
     waive
    0.09
    _modules
    0.07
     contested
    0.07
     contamination
    0.07
     competed
    0.07
     is
    0.07
     одно
    0.07
    ません
    0.07
     contaminated
    0.07
     contamin
    0.07
    Act Density 0.000%

    No Known Activations