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

    Neuronpedia

    INDEX
    Explanations

    neutral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     retailers
    -0.07
     степени
    -0.06
    답
    -0.06
     bureau
    -0.06
     Holden
    -0.06
     Rob
    -0.06
     nebude
    -0.06
     pity
    -0.06
     objeto
    -0.06
     của
    -0.06
    POSITIVE LOGITS
    Neutral
    0.07
    neutral
    0.07
     SIMD
    0.06
    ilation
    0.06
    Indicator
    0.06
    etrain
    0.06
    <Int
    0.06
     Plaintiff
    0.06
    (-(
    0.06
    .Screen
    0.06
    Act Density 0.000%

    No Known Activations