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

    Neuronpedia

    INDEX
    Explanations

    news headlines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \File
    -0.08
    umen
    -0.07
    文物
    -0.07
    DAY
    -0.07
    ivered
    -0.07
    归来
    -0.07
    <Car
    -0.06
     �
    -0.06
     Carpet
    -0.06
    隊
    -0.06
    POSITIVE LOGITS
     TOKEN
    0.07
    .sf
    0.06
    盟
    0.06
    `),↵
    0.06
    垦
    0.06
    /z
    0.06
     suggestions
    0.06
    跐
    0.06
    .token
    0.06
    堐
    0.06
    Act Density 0.090%

    No Known Activations