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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Changed
    -0.07
     пен
    -0.07
    Sr
    -0.06
     overlay
    -0.06
     unparalleled
    -0.06
     sharing
    -0.06
    )]↵↵
    -0.06
     visiting
    -0.06
    ;charset
    -0.06
     palindrome
    -0.06
    POSITIVE LOGITS
     віль
    0.06
    港
    0.06
    ослав
    0.06
    cannot
    0.06
    Cannot
    0.06
    	loop
    0.06
    	rv
    0.06
    Bei
    0.06
    χε
    0.06
     meas
    0.06
    Act Density 0.080%

    No Known Activations