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

    Neuronpedia

    INDEX
    Explanations

    calculus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scholarly
    -0.07
     bridges
    -0.07
     passions
    -0.07
    uge
    -0.06
    nas
    -0.06
    >↵↵↵↵
    -0.06
    buch
    -0.06
     links
    -0.06
    	player
    -0.06
     advocate
    -0.06
    POSITIVE LOGITS
     ál
    0.08
    乔治
    0.07
    RTL
    0.07
    Tanggal
    0.07
    ıl
    0.07
    mática
    0.07
    _hdl
    0.07
    .Chart
    0.07
    Abstract
    0.07
     alın
    0.07
    Act Density 0.001%

    No Known Activations