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

    Neuronpedia

    INDEX
    Explanations

    l

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mosques
    -0.07
    oria
    -0.07
     متر
    -0.07
    North
    -0.07
     Россия
    -0.06
    菌
    -0.06
    imiters
    -0.06
     учнів
    -0.06
    SHORT
    -0.06
    语言
    -0.06
    POSITIVE LOGITS
     Behavioral
    0.08
     pleaded
    0.07
    (URL
    0.06
    ‹
    0.06
    .el
    0.06
    .pat
    0.06
     examines
    0.06
     cudaMemcpy
    0.06
     decorate
    0.06
    arefa
    0.06
    Act Density 0.021%

    No Known Activations