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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =index
    -0.07
     Blade
    -0.06
     Worst
    -0.06
    Parts
    -0.06
     몸
    -0.06
     групи
    -0.06
     iets
    -0.06
     nause
    -0.06
     proliferation
    -0.06
    PhoneNumber
    -0.06
    POSITIVE LOGITS
    FilterWhere
    0.07
    (no
    0.06
     Directory
    0.06
    .mi
    0.06
     notwithstanding
    0.06
     VAT
    0.06
    ल
    0.06
    рахов
    0.06
     addButton
    0.06
     requesting
    0.06
    Act Density 0.003%

    No Known Activations