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

    Neuronpedia

    INDEX
    Explanations

    key role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndGlobalSection
    0.33
    ਝ
    0.32
    ╼
    0.32
    iciente
    0.32
    ادث
    0.32
    انوں
    0.32
    प्ताह
    0.31
     हुआ
    0.31
     नम
    0.31
    requestFocus
    0.31
    POSITIVE LOGITS
     role
    4.13
     roles
    3.89
    role
    3.80
    Role
    3.78
     Role
    3.77
     Roles
    3.61
     роль
    3.56
    Roles
    3.55
    角色
    3.53
    roles
    3.53
    Act Density 0.271%

    No Known Activations