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

    Neuronpedia

    INDEX
    Explanations

    SHIFT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (concat
    -0.07
     Table
    -0.06
    ंडल
    -0.06
     Peg
    -0.06
    speaker
    -0.06
    CLK
    -0.06
     برنامج
    -0.06
     endoth
    -0.06
     Massage
    -0.06
    /effects
    -0.06
    POSITIVE LOGITS
    اي
    0.07
    alan
    0.07
    identally
    0.06
     benefiting
    0.06
    prise
    0.06
    	option
    0.06
     prevents
    0.06
     права
    0.06
    ']}↵
    0.06
     potrze
    0.06
    Act Density 0.008%

    No Known Activations