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

    Neuronpedia

    INDEX
    Explanations

    Wiki code/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sol
    -0.07
    จาก
    -0.07
     cerc
    -0.06
    通知
    -0.06
     Luca
    -0.06
     instances
    -0.06
     assessments
    -0.06
     Morocco
    -0.06
     Diamonds
    -0.06
     、
    -0.06
    POSITIVE LOGITS
     bản
    0.08
    oredProcedure
    0.06
    ="">↵
    0.06
     viper
    0.06
     PodsDummy
    0.06
     Vern
    0.06
    kie
    0.06
    ugo
    0.06
    ěr
    0.06
    Comple
    0.06
    Act Density 0.007%

    No Known Activations