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

    Neuronpedia

    INDEX
    Explanations

    negative reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    बस
    -0.08
     बसे
    -0.08
     Detailed
    -0.08
     order
    -0.08
    .google
    -0.07
     beautiful
    -0.07
     आदेश
    -0.07
     divider
    -0.07
     인터
    -0.07
     informed
    -0.07
    POSITIVE LOGITS
     mediocre
    0.12
     manque
    0.10
     dull
    0.10
     poor
    0.09
     unat
    0.09
     objectively
    0.09
    实力
    0.09
     kualitas
    0.09
     kalidad
    0.09
     rendah
    0.09
    Act Density 0.242%

    No Known Activations