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

    Neuronpedia

    INDEX
    Explanations

    role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intelligible
    0.80
     senc
    0.76
    odyne
    0.72
     পদ্ধ
    0.71
     agonizing
    0.70
    STM
    0.70
     Besitzer
    0.69
     consumable
    0.69
     judgements
    0.68
    ihkan
    0.68
    POSITIVE LOGITS
     role
    3.14
     Role
    2.97
    Role
    2.80
    role
    2.69
     roles
    2.60
     роль
    2.49
     rôle
    2.46
     ruolo
    2.37
     ROLE
    2.33
     Roles
    2.30
    Act Density 0.398%

    No Known Activations