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

    Neuronpedia

    INDEX
    Explanations

    Article excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slave
    -0.07
    級
    -0.07
    Vac
    -0.06
     Saving
    -0.06
     Kashmir
    -0.06
     Asia
    -0.06
     cur
    -0.06
    Dans
    -0.06
    448
    -0.06
     dissent
    -0.06
    POSITIVE LOGITS
    "}),↵
    0.07
    黄
    0.07
     sır
    0.06
    ])))
    0.06
    cej
    0.06
    ح
    0.06
    ділу
    0.06
    icions
    0.06
    시험
    0.06
    estructor
    0.06
    Act Density 0.151%

    No Known Activations