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

    Neuronpedia

    INDEX
    Explanations

    references to roles or positions within a system, especially in a context of identity or functionality

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

    role assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noDo
    -0.40
     Uang
    -0.37
    jsxFileName
    -0.36
     Olympic
    -0.33
    置いて
    -0.32
     olympic
    -0.32
     hourglass
    -0.32
    mobileqq
    -0.32
    σμα
    -0.31
    Jeografia
    -0.31
    POSITIVE LOGITS
    Roles
    2.22
    roles
    1.89
     Roles
    1.80
     Role
    1.52
    Role
    1.52
     roles
    1.50
    ROLES
    1.48
     role
    1.44
     ROLE
    1.32
    ROLE
    1.27
    Act Density 0.004%

    No Known Activations