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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UpDown
    -0.07
    姆
    -0.06
     đá
    -0.06
    隊
    -0.06
     projectile
    -0.06
     hoàng
    -0.06
    outines
    -0.06
     Yankee
    -0.06
     TPP
    -0.06
    -design
    -0.06
    POSITIVE LOGITS
    abilité
    0.06
    amaha
    0.06
    ingerprint
    0.06
    >',↵
    0.06
    >';↵
    0.06
    =""/>↵
    0.06
    ]]></
    0.06
    ,,,
    0.06
    ,,,,
    0.06
    _cal
    0.06
    Act Density 0.032%

    No Known Activations