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

    Neuronpedia

    INDEX
    Explanations

    say "start"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TypeDef
    -0.07
     pulumi
    -0.07
    ESCO
    -0.06
    .Container
    -0.06
    productive
    -0.06
     Dudley
    -0.06
    hind
    -0.06
    途
    -0.06
     Bund
    -0.06
    olest
    -0.06
    POSITIVE LOGITS
    τέ
    0.06
    ****↵
    0.06
     coverage
    0.06
    áže
    0.06
     кіль
    0.06
    club
    0.06
     capability
    0.06
    プラ
    0.06
    orage
    0.06
    -ob
    0.05
    Act Density 0.117%

    No Known Activations