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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الاجتماعية
    -0.09
     IRS
    -0.09
     cherish
    -0.08
    ativos
    -0.08
    E
    -0.08
    adaş
    -0.08
     मिलने
    -0.07
     ಆದ
    -0.07
    -error
    -0.07
    -model
    -0.07
    POSITIVE LOGITS
    贯
    0.11
     специально
    0.09
     flatter
    0.08
    穿
    0.08
     রেখ
    0.08
     embedded
    0.08
    ')</
    0.07
     Jour
    0.07
     конце
    0.07
    ร้าน
    0.07
    Act Density 0.021%

    No Known Activations