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

    Neuronpedia

    INDEX
    Explanations

    say "ending /L"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Proceed
    -0.08
     dolayı
    -0.08
     Implementation
    -0.07
     terra
    -0.07
     consort
    -0.07
    乗り
    -0.07
     descend
    -0.07
     acompañ
    -0.07
     congress
    -0.07
     conjug
    -0.07
    POSITIVE LOGITS
     ]).
    0.07
    "display
    0.07
    糜
    0.07
    daily
    0.07
     Palest
    0.06
    )，
    0.06
    马来西亚
    0.06
     talked
    0.06
    .UNRELATED
    0.06
     strokeLine
    0.06
    Act Density 0.003%

    No Known Activations