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

    Neuronpedia

    INDEX
    Explanations

    classified

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    762
    -0.07
    μένες
    -0.06
    pathname
    -0.06
    901
    -0.06
     году
    -0.06
     yılı
    -0.06
    861
    -0.06
     Shirt
    -0.06
    urrect
    -0.06
    -make
    -0.06
    POSITIVE LOGITS
     destroy
    0.08
    igslist
    0.08
     Craigslist
    0.08
     compuls
    0.07
    astreet
    0.07
    .Categories
    0.06
    )_
    0.06
    .createUser
    0.06
    _COLUMN
    0.06
     possessions
    0.06
    Act Density 0.014%

    No Known Activations