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

    Neuronpedia

    INDEX
    Explanations

    adopting a role or persona

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getSelectedItem
    0.61
    ArrowToggle
    0.60
    čiau
    0.59
    viridis
    0.59
    resized
    0.58
    otroph
    0.58
    ınt
    0.58
     Bands
    0.58
    cvtColor
    0.57
    뺄
    0.57
    POSITIVE LOGITS
     role
    1.78
     Role
    1.71
     persona
    1.68
    role
    1.61
     roles
    1.60
    Role
    1.55
    扮演
    1.52
    persona
    1.49
     ROLE
    1.48
     personas
    1.45
    Act Density 0.531%

    No Known Activations