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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lib
    -0.06
    ΑΘ
    -0.06
    Expansion
    -0.06
     <+
    -0.06
    -Jan
    -0.06
     ""
    -0.06
     zwe
    -0.06
    orgeous
    -0.05
    胡
    -0.05
    yn
    -0.05
    POSITIVE LOGITS
     {[%
    0.07
     Pixel
    0.07
    	statement
    0.07
     {{$
    0.07
    (sync
    0.07
    ственного
    0.07
    itional
    0.07
    .sale
    0.06
    :::::|
    0.06
    повід
    0.06
    Act Density 0.035%

    No Known Activations