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

    Neuronpedia

    INDEX
    Explanations

    Replying to emails/messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utm
    -0.08
    ometers
    -0.08
    ,
↵
↵
    -0.08
    ют
    -0.07
    ము
    -0.07
    ader
    -0.07
     Motto
    -0.07
     Measures
    -0.07
     catalytic
    -0.07
    ıt
    -0.07
    POSITIVE LOGITS
    邮件
    0.11
     بريد
    0.11
     письмо
    0.10
     mail
    0.10
     મોક
    0.10
    メール
    0.10
     წერ
    0.10
     صي
    0.09
     email
    0.09
     courrier
    0.09
    Act Density 0.023%

    No Known Activations