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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     stale
    -0.06
     banquet
    -0.06
    下载
    -0.06
    sports
    -0.06
    .prod
    -0.06
    意味
    -0.06
     competence
    -0.06
     bribery
    -0.06
     snad
    -0.06
    POSITIVE LOGITS
     Colo
    0.07
     dro
    0.06
     Enums
    0.06
    .Location
    0.06
    Als
    0.06
     Dr
    0.06
    리아
    0.06
     Vulner
    0.06
    .Param
    0.06
     cree
    0.06
    Act Density 0.018%

    No Known Activations