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

    Neuronpedia

    INDEX
    Explanations

    say "Today is"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ौत
    -0.06
    lední
    -0.06
     Toni
    -0.06
    burgh
    -0.06
    operators
    -0.06
    nik
    -0.06
    high
    -0.06
     thư
    -0.06
    읍
    -0.06
    oty
    -0.06
    POSITIVE LOGITS
     acab
    0.07
    +c
    0.07
     вваж
    0.07
    }{↵
    0.06
     elo
    0.06
    dataTable
    0.06
     beautiful
    0.06
    (guild
    0.06
     b
    0.06
    .iterator
    0.06
    Act Density 0.013%

    No Known Activations