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

    Neuronpedia

    INDEX
    Explanations

    -Star

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     readFile
    -0.07
    "];
↵
    -0.07
    ('.'
    -0.07
    ];
    -0.07
     studios
    -0.07
     khám
    -0.06
    现身
    -0.06
    addir
    -0.06
    天津
    -0.06
     divides
    -0.06
    POSITIVE LOGITS
    Ⓢ
    0.07
     By
    0.07
    任何
    0.07
     alternate
    0.07
    鸭
    0.07
    社会保险
    0.07
    앜
    0.07
    גיב
    0.07
    🕷
    0.06
     가지
    0.06
    Act Density 0.001%

    No Known Activations