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

    Neuronpedia

    INDEX
    Explanations

    marginalized and vulnerable groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CUIT
    0.45
    ストレ
    0.43
    Sigma
    0.43
    Serialization
    0.41
    érature
    0.41
    Filters
    0.40
     NaOH
    0.39
    ᔨ
    0.39
     Druck
    0.39
    NaOH
    0.39
    POSITIVE LOGITS
     immigrants
    1.46
     disabled
    1.44
     refugees
    1.43
     homeless
    1.40
     minorities
    1.35
     elderly
    1.34
     Disabled
    1.33
     refugee
    1.30
     दिव्यांग
    1.30
    disabled
    1.27
    Act Density 0.021%

    No Known Activations