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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Matrix
    -0.06
     Numbers
    -0.06
     numbers
    -0.06
     quốc
    -0.06
     puedes
    -0.06
     También
    -0.06
     Федерации
    -0.06
     bold
    -0.06
    ,");↵
    -0.06
     Button
    -0.06
    POSITIVE LOGITS
    experience
    0.07
     afterwards
    0.07
    祭
    0.06
    PRESSION
    0.06
    品牌
    0.06
     legit
    0.06
     �
    0.06
     histoire
    0.06
     उपय
    0.06
    /GL
    0.06
    Act Density 0.017%

    No Known Activations