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

    Neuronpedia

    INDEX
    Explanations

    End/Start of sentence, or beginning of email

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    表示
    -0.09
    ENDING
    -0.08
    -occ
    -0.08
    ம்பெ
    -0.08
    ，我们
    -0.08
    SEE
    -0.08
    NOS
    -0.08
    -Holland
    -0.08
    重复
    -0.07
    .other
    -0.07
    POSITIVE LOGITS
     ;-)
    0.13
     😉
    0.12
     😂
    0.12
     kidding
    0.12
    Haha
    0.11
     �
    0.11
     ;-)↵↵
    0.11
     �
    0.11
     ;)↵↵
    0.10
     ;)
    0.10
    Act Density 0.648%

    No Known Activations