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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cincinnati
    -0.08
     saison
    -0.07
     austerity
    -0.07
     Executive
    -0.07
    gart
    -0.07
    荃
    -0.07
    TRS
    -0.07
     Wine
    -0.06
    福
    -0.06
     Boston
    -0.06
    POSITIVE LOGITS
                    ↵                ↵
    0.07
    ,filename
    0.07
    licer
    0.07
    史上
    0.07
    (correct
    0.07
    LIKE
    0.07
    Usually
    0.07
    -cr
    0.06
    ':↵
    0.06
    (of
    0.06
    Act Density 0.021%

    No Known Activations