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

    Neuronpedia

    INDEX
    Explanations

    terms associated with roles and responsibilities

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

    "role"

    np_acts-logits-general · gemini-2.0-flash

    role in models or limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ihnachten
    -0.69
     سكانية
    -0.68
    misa
    -0.58
    انيف
    -0.56
     externi
    -0.55
     prova
    -0.55
    AnchorTagHelper
    -0.55
    اری
    -0.54
    tiefel
    -0.53
     jawaban
    -0.52
    POSITIVE LOGITS
     roles
    1.38
     role
    1.25
     Roles
    1.25
     ROLE
    1.25
     Role
    1.16
     getRole
    1.13
    Roles
    1.05
    Role
    1.03
     played
    0.97
    roles
    0.95
    Act Density 0.071%

    No Known Activations