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

    Neuronpedia

    INDEX
    Explanations

    underscores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poles
    -0.06
     processed
    -0.06
     container
    -0.06
     Podle
    -0.06
     jaws
    -0.06
     mains
    -0.06
    an
    -0.06
    armacy
    -0.06
     NA
    -0.06
     Lyons
    -0.06
    POSITIVE LOGITS
    аров
    0.07
    票
    0.07
    _BLOCKS
    0.06
    aaaa
    0.06
    yyval
    0.06
    EEK
    0.06
    当然
    0.06
     {|
    0.06
     Warm
    0.06
    tuğ
    0.06
    Act Density 0.006%

    No Known Activations