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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    潵
    -0.07
    Gift
    -0.07
     Rencontre
    -0.07
    ]+
    -0.07
    词条
    -0.07
     ksz
    -0.07
     useless
    -0.07
     ResourceManager
    -0.07
    intelligence
    -0.07
     Eyl
    -0.07
    POSITIVE LOGITS
    .Margin
    0.08
    태
    0.07
     Fraser
    0.07
    뱁
    0.07
    叫声
    0.07
     Clay
    0.07
    �
    0.06
    .lines
    0.06
    0.06
    periences
    0.06
    Act Density 0.069%

    No Known Activations