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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jul
    -0.07
    Utility
    -0.06
    рогра
    -0.06
     rychle
    -0.06
     };
↵
↵
    -0.06
    .AnchorStyles
    -0.06
     اصفه
    -0.06
    -scrollbar
    -0.06
    它们
    -0.06
     Phot
    -0.06
    POSITIVE LOGITS
     nights
    0.06
     possui
    0.06
    PMENT
    0.06
    .active
    0.06
    ��取
    0.06
     coch
    0.06
     dragon
    0.06
    inery
    0.06
     bem
    0.06
     Former
    0.06
    Act Density 0.018%

    No Known Activations