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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     århus
    -0.06
    /W
    -0.06
    Arthur
    -0.06
    /widget
    -0.06
     Rue
    -0.06
     Median
    -0.06
    ('-
    -0.06
     dataTable
    -0.06
    primir
    -0.06
     rop
    -0.06
    POSITIVE LOGITS
    ！”
    0.06
     rays
    0.06
    Г
    0.06
     WHETHER
    0.06
     moved
    0.06
    CLE
    0.06
    unless
    0.06
     Ish
    0.06
    Reporter
    0.06
    bio
    0.06
    Act Density 0.008%

    No Known Activations