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

    Neuronpedia

    INDEX
    Explanations

    user_email, role, password, name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    雕
    0.45
     outcrop
    0.44
    ARGET
    0.40
     VALVE
    0.40
    priced
    0.39
    rangea
    0.39
     escul
    0.38
    作者
    0.38
    LLCATS
    0.38
    险
    0.38
    POSITIVE LOGITS
     email
    0.75
     Roles
    0.75
     roles
    0.72
    email
    0.65
     ईमेल
    0.65
    Email
    0.65
     Email
    0.65
     role
    0.62
    电子邮件
    0.61
    Roles
    0.59
    Act Density 0.006%

    No Known Activations