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

    Neuronpedia

    INDEX
    Explanations

    say "Week, Step, Day"

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    ᅪ
    -0.08
     văn
    -0.08
    是韩国娱
    -0.07
    être
    -0.07
     distingu
    -0.07
     kab
    -0.07
     perg
    -0.07
     nep
    -0.07
    ᶆ
    -0.07
    漢
    -0.06
    POSITIVE LOGITS
    延长
    0.08
    神器
    0.07
    +self
    0.07
     RPM
    0.07
    Rate
    0.07
    足足
    0.07
     weekly
    0.07
    可能です
    0.07
     Simply
    0.07
     solids
    0.07
    Act Density 0.066%

    No Known Activations