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

    Neuronpedia

    INDEX
    Explanations

    possessives/contractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     эти
    -0.08
     CHUNK
    -0.07
    inez
    -0.07
    etre
    -0.06
    .styleable
    -0.06
    etro
    -0.06
     чт
    -0.06
    UA
    -0.06
     تاریخی
    -0.06
     Bombay
    -0.06
    POSITIVE LOGITS
    ========↵
    0.07
    /books
    0.06
     submitting
    0.06
    /*↵↵
    0.06
    :null
    0.06
     Independ
    0.06
     nào
    0.06
    ,output
    0.05
    Impl
    0.05
     dr
    0.05
    Act Density 0.221%

    No Known Activations