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

    Neuronpedia

    INDEX
    Explanations

    describing matter attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ログイン
    0.50
     પસંદ
    0.45
     usernames
    0.44
     transactions
    0.43
    余额
    0.43
     로그인
    0.43
    userdata
    0.43
    查詢
    0.43
    UserInfo
    0.42
     delinquency
    0.42
    POSITIVE LOGITS
     description
    0.63
    setDescription
    0.63
     Description
    0.59
    description
    0.58
     describ
    0.58
    Description
    0.56
     Beschreibung
    0.56
     descripción
    0.50
     getDescription
    0.49
     describe
    0.49
    Act Density 0.195%

    No Known Activations