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

    Neuronpedia

    INDEX
    Explanations

    code, instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utar
    -0.06
    //{{
    -0.06
     �
    -0.06
    FINITE
    -0.06
    っぱい
    -0.06
     acess
    -0.06
     racially
    -0.06
    üstü
    -0.06
     lids
    -0.06
     ure
    -0.06
    POSITIVE LOGITS
     airplane
    0.07
    �
    0.07
    ripple
    0.06
    ()>↵
    0.06
    coin
    0.06
    grounds
    0.06
    िस
    0.06
    	of
    0.06
    Proceed
    0.06
     restroom
    0.06
    Act Density 0.000%

    No Known Activations