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

    Neuronpedia

    INDEX
    Explanations

    percent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Caldwell
    -0.06
    胡
    -0.06
    NO
    -0.06
    ्पत
    -0.06
    โค
    -0.06
    _products
    -0.06
    &B
    -0.06
     among
    -0.06
    'all
    -0.06
    ันทร
    -0.06
    POSITIVE LOGITS
     getX
    0.07
     дов
    0.07
    READING
    0.07
     Resume
    0.07
     chuyên
    0.07
    .tasks
    0.06
    ertainment
    0.06
    북
    0.06
    		
↵
↵
    0.06
    環境
    0.06
    Act Density 0.052%

    No Known Activations