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

    Neuronpedia

    INDEX
    Explanations

    limitless

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     интер
    -0.07
     yards
    -0.06
    ITCH
    -0.06
     breath
    -0.06
    tro
    -0.06
     {"
    -0.06
     drunk
    -0.06
     elf
    -0.06
    dll
    -0.06
    Mary
    -0.06
    POSITIVE LOGITS
     державного
    0.08
     kcal
    0.07
    (Initialized
    0.07
    milliseconds
    0.06
    ьв
    0.06
    ован
    0.06
     Gas
    0.06
    .redis
    0.06
    کن
    0.06
     Bucket
    0.06
    Act Density 0.003%

    No Known Activations