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

    Neuronpedia

    INDEX
    Explanations

    making a choice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Polo
    -0.07
    Producto
    -0.07
    מועמד
    -0.07
    污染物
    -0.07
     crédito
    -0.06
    态度
    -0.06
    洗衣
    -0.06
    净资产
    -0.06
    mp
    -0.06
    Michael
    -0.06
    POSITIVE LOGITS
    UNCT
    0.07
    —at
    0.06
    ARNING
    0.06
    辘
    0.06
    "]=>
    0.06
    .ColumnHeadersHeightSizeMode
    0.06
    AVIS
    0.06
    ……
    0.06
    -days
    0.06
    闶
    0.06
    Act Density 0.096%

    No Known Activations