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

    Neuronpedia

    INDEX
    Explanations

    Borders (programming context)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dead
    -0.07
    	env
    -0.06
     Jack
    -0.06
     o
    -0.06
    Analyzer
    -0.06
    eric
    -0.06
     inviting
    -0.06
     David
    -0.06
     Ram
    -0.06
    (nc
    -0.06
    POSITIVE LOGITS
     çık
    0.06
     UserProfile
    0.06
    .cleaned
    0.06
     ｌ
    0.06
     вий
    0.06
     chlap
    0.06
    /movie
    0.06
    ynam
    0.06
    Sprite
    0.06
    скую
    0.06
    Act Density 0.034%

    No Known Activations