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

    Neuronpedia

    INDEX
    Explanations

    odds ratios and intervals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equipo
    -0.08
    镜头
    -0.07
    AxisAlignment
    -0.07
     зад
    -0.07
     Tracking
    -0.06
     Sent
    -0.06
    .transform
    -0.06
    派出
    -0.06
    (my
    -0.06
     stream
    -0.06
    POSITIVE LOGITS
    病例
    0.08
     том
    0.07
    ဠ
    0.07
     nông
    0.07
     Rossi
    0.07
    妊
    0.07
    aklı
    0.07
    .OS
    0.07
     potrà
    0.07
    셧
    0.07
    Act Density 0.323%

    No Known Activations