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

    Neuronpedia

    INDEX
    Explanations

    false starts/uncertainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ž
    -0.07
    performance
    -0.06
    าคม
    -0.06
     jov
    -0.06
    tin
    -0.06
    标题
    -0.06
     rendre
    -0.06
    ्च
    -0.06
    %=
    -0.06
     waivers
    -0.06
    POSITIVE LOGITS
     "../../../
    0.07
     usted
    0.07
     쓰
    0.07
    ))/(
    0.06
    totalCount
    0.06
    ("^
    0.06
     Ul
    0.06
     оцен
    0.06
     abusive
    0.06
    Türkiye
    0.06
    Act Density 0.165%

    No Known Activations