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
    逝
    -0.07
    dataProvider
    -0.07
    adora
    -0.07
     deterior
    -0.07
    Advisor
    -0.07
     ALSO
    -0.07
    rh
    -0.07
    がら
    -0.07
     überh
    -0.07
    (factor
    -0.07
    POSITIVE LOGITS
     кино
    0.07
    -Qaeda
    0.07
     Asian
    0.07
     Kerala
    0.07
    workers
    0.07
    Christmas
    0.06
     labelled
    0.06
    קלי
    0.06
    ,input
    0.06
     XF
    0.06
    Act Density 0.031%

    No Known Activations