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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    洇
    -0.07
    ﰀ
    -0.07
    至
    -0.06
    見る
    -0.06
    ());↵
    -0.06
    ｅ
    -0.06
    庄
    -0.06
    cd
    -0.06
    -de
    -0.06
    U
    -0.06
    POSITIVE LOGITS
     hurricane
    0.07
     sponsor
    0.07
     qualifying
    0.07
    /rs
    0.07
    protocols
    0.07
     chang
    0.07
    HAS
    0.07
     początk
    0.07
     sponsoring
    0.07
    ernal
    0.07
    Act Density 0.014%

    No Known Activations