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

    Neuronpedia

    INDEX
    Explanations

    user or username

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LPTMR
    0.48
     rameaux
    0.47
    llrp
    0.46
    vVertex
    0.45
    ՜
    0.45
     prostaglandin
    0.44
    Lemma
    0.44
    atedral
    0.44
    estomac
    0.44
    腟
    0.44
    POSITIVE LOGITS
     User
    1.00
     user
    0.97
     username
    0.94
    用户的
    0.89
     kullanıcı
    0.89
     login
    0.89
     пользователя
    0.86
     usernames
    0.86
     用户
    0.85
    ログイン
    0.84
    Act Density 0.315%

    No Known Activations