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

    Neuronpedia

    INDEX
    Explanations

    role

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     speeds
    -0.07
     exponentially
    -0.07
     exponential
    -0.07
     Ngo
    -0.07
    .Dto
    -0.07
    性色
    -0.07
     EBITDA
    -0.07
     Spe
    -0.07
    泳
    -0.07
    โปรโมชั่น
    -0.07
    POSITIVE LOGITS
     निभ
    0.15
     भूमिका
    0.12
    角色
    0.11
     roles
    0.11
    roles
    0.11
    <Role
    0.11
     역할
    0.11
     पत्नी
    0.11
    -role
    0.11
    _roles
    0.10
    Act Density 0.017%

    No Known Activations