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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bolt
    -0.07
     boxed
    -0.07
     midpoint
    -0.07
    andWhere
    -0.07
     flips
    -0.06
     hire
    -0.06
     psych
    -0.06
    Charles
    -0.06
     chair
    -0.06
    xcd
    -0.06
    POSITIVE LOGITS
     :↵↵↵↵
    0.07
    �
    0.07
    /Delete
    0.06
    roducing
    0.06
    <K
    0.06
    .MEDIA
    0.06
     iNdEx
    0.06
     QStringList
    0.06
     ------>
    0.06
     webpack
    0.06
    Act Density 0.135%

    No Known Activations