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

    Neuronpedia

    INDEX
    Explanations

    key roles and their importance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "role" or "roles"

    np_acts-logits-general · gemini-2.0-flash

    key / supporting / important role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.57
    djangoproject
    -0.56
     Italijanski
    -0.54
    Indent
    -0.51
     Indexed
    -0.49
     colored
    -0.48
    SerializeField
    -0.48
     eigenvectors
    -0.46
     colheres
    -0.46
    IBarButtonItem
    -0.45
    POSITIVE LOGITS
     role
    2.40
     roles
    2.33
    role
    2.00
     Role
    1.94
     Roles
    1.91
     ROLE
    1.87
     rôle
    1.84
     rôles
    1.84
    Role
    1.82
    roles
    1.81
    Act Density 0.240%

    No Known Activations