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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     округ
    -0.07
     stagger
    -0.07
    團
    -0.07
    άλ
    -0.06
    춘
    -0.06
    ?>"/>↵
    -0.06
     aval
    -0.06
     nhuận
    -0.06
     Tas
    -0.06
    ＾
    -0.06
    POSITIVE LOGITS
    /lists
    0.07
     coveted
    0.06
    egal
    0.06
    -country
    0.06
     необхід
    0.06
     noteworthy
    0.06
    /l
    0.06
    ‌ب
    0.06
    redicate
    0.06
    /lab
    0.06
    Act Density 0.020%

    No Known Activations