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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ーク
    -0.07
     Ryu
    -0.07
    原本
    -0.06
     asshole
    -0.06
    єш
    -0.06
     insiders
    -0.06
     목록
    -0.06
    CREMENT
    -0.06
     hã
    -0.06
     Hammer
    -0.06
    POSITIVE LOGITS
     dato
    0.08
     erv
    0.07
     indo
    0.07
     Nev
    0.06
    .XML
    0.06
     mouseClicked
    0.06
     sean
    0.06
     Reference
    0.06
     loại
    0.06
     owl
    0.06
    Act Density 0.001%

    No Known Activations