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

    Neuronpedia

    INDEX
    Explanations

    hobbies and activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distributes
    -0.08
    ))));↵
    -0.08
     Real
    -0.08
    .netty
    -0.08
    लेट
    -0.08
     توزيع
    -0.07
    leck
    -0.07
     निर्देशन
    -0.07
     माइ
    -0.07
    venteen
    -0.07
    POSITIVE LOGITS
     hobbies
    0.09
     탐
    0.09
     cuisines
    0.09
    探索
    0.09
     ham
    0.08
     podcasts
    0.08
    (country
    0.08
    ];
    0.08
     git
    0.07
     explore
    0.07
    Act Density 0.108%

    No Known Activations