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

    Neuronpedia

    INDEX
    Explanations

    email address placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     roues
    0.37
     Mila
    0.34
    ৌম
    0.34
    middleware
    0.34
    Middleware
    0.33
     gonf
    0.33
    Ella
    0.33
     midwives
    0.33
     symptomatic
    0.33
     obstáculos
    0.33
    POSITIVE LOGITS
     email
    0.90
    email
    0.85
     Email
    0.84
     ईमेल
    0.74
    Email
    0.73
    电子邮件
    0.72
     emails
    0.60
    setEmail
    0.59
    メール
    0.59
    EMAIL
    0.59
    Act Density 0.002%

    No Known Activations