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

    Neuronpedia

    INDEX
    Explanations

    words referring to oneself or family members

    oai_token-act-pair · gemini-2.0-flash

    reflexive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Express
    -0.46
     fe
    -0.42
     trưởng
    -0.40
    <bos>
    -0.39
    loy
    -0.37
    鞠
    -0.37
    %
    -0.36
    or
    -0.36
    Expr
    -0.36
    esp
    -0.35
    POSITIVE LOGITS
     nahilalakip
    0.84
    Diweddarwch
    0.75
    ]")]
    0.70
    featureID
    0.68
     photolibrary
    0.68
    fromnode
    0.68
     CreateTagHelper
    0.67
    참고
    0.67
    sizeCache
    0.66
    MigrationBuilder
    0.66
    Act Density 1.406%

    No Known Activations