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

    Neuronpedia

    INDEX
    Explanations

    0 and 1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IRS
    -0.06
    至
    -0.06
    시간
    -0.06
     instruction
    -0.06
    Seek
    -0.06
    大家
    -0.06
     inspired
    -0.06
     Mits
    -0.06
    potential
    -0.06
    .navigate
    -0.06
    POSITIVE LOGITS
    .Exceptions
    0.07
     %%↵
    0.07
    .shop
    0.07
    .onClick
    0.06
     <<<
    0.06
     habe
    0.06
    ,/
    0.06
     ~~
    0.06
     Dummy
    0.06
    acr
    0.06
    Act Density 0.018%

    No Known Activations