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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insertion
    -0.08
    (seq
    -0.08
     aviation
    -0.07
     Wind
    -0.07
     Gabriel
    -0.07
     Shadows
    -0.07
     저
    -0.07
    IRON
    -0.07
    Prepare
    -0.07
     בש
    -0.07
    POSITIVE LOGITS
    �
    0.08
     />)↵
    0.07
    	mp
    0.07
    깥
    0.07
     libertarian
    0.06
    alternative
    0.06
     totalCount
    0.06
    ديمق
    0.06
    缝
    0.06
    currentTime
    0.06
    Act Density 0.071%

    No Known Activations