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

    Neuronpedia

    INDEX
    Explanations

    transforming into something else

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     naam
    -0.07
     propose
    -0.07
     zas
    -0.07
     categorized
    -0.07
     decided
    -0.07
    žený
    -0.06
    poke
    -0.06
     comparable
    -0.06
    .isfile
    -0.06
    Deferred
    -0.06
    POSITIVE LOGITS
     piel
    0.06
     PageInfo
    0.06
    _precision
    0.06
     Clone
    0.06
    (panel
    0.06
     gameOver
    0.06
     августа
    0.06
    %!
    0.06
    合格
    0.06
     Flickr
    0.06
    Act Density 0.007%

    No Known Activations