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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uka
    -0.07
     Bên
    -0.07
    察
    -0.07
     BYTE
    -0.06
    	td
    -0.06
    ikh
    -0.06
    Cadastro
    -0.06
    signin
    -0.06
    ตลาด
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Vacation
    0.07
     Reading
    0.06
    .executeUpdate
    0.06
    арів
    0.06
    Reading
    0.06
     addition
    0.06
    ingredients
    0.06
    browser
    0.06
    .Zip
    0.06
    .NotNull
    0.06
    Act Density 0.039%

    No Known Activations