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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -General
    -0.07
    enade
    -0.07
    ╉
    -0.06
    𝕷
    -0.06
    箬
    -0.06
    EMPLATE
    -0.06
    erto
    -0.06
    (units
    -0.06
     Goku
    -0.06
    /repos
    -0.06
    POSITIVE LOGITS
    庙
    0.08
    曹
    0.07
     }]↵
    0.07
     красив
    0.07
    清代
    0.06
    ANCED
    0.06
     бизнес
    0.06
    MIN
    0.06
    配套
    0.06
    ounded
    0.06
    Act Density 0.030%

    No Known Activations