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

    Neuronpedia

    INDEX
    Explanations

    parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    енном
    -0.07
     評価
    -0.07
     lam
    -0.06
     알고
    -0.06
     Lect
    -0.06
    urse
    -0.06
     melanch
    -0.06
    ens
    -0.06
    larıyla
    -0.06
     çab
    -0.06
    POSITIVE LOGITS
    (register
    0.06
    ابعة
    0.06
     سل
    0.06
    using
    0.06
    clusters
    0.06
    ㆍ
    0.06
     FOOD
    0.06
    říd
    0.06
     explode
    0.06
    };↵↵↵↵
    0.06
    Act Density 0.017%

    No Known Activations