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

    Neuronpedia

    INDEX
    Explanations

    references to groups or collections, especially in the context of specific categories or conditions

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

    legion and legions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.57
     dataSnapshot
    -0.50
    makeConstraints
    -0.47
    kegaard
    -0.47
    testens
    -0.45
    DoubleQuotes
    -0.44
     numberWith
    -0.44
    Marx
    -0.43
     Nut
    -0.43
     
    -0.42
    POSITIVE LOGITS
     legion
    1.91
     Legion
    1.83
    Legion
    1.80
    legion
    1.67
     legions
    1.30
     Légion
    1.00
    军团
    0.95
     LEG
    0.89
     lég
    0.71
    naires
    0.71
    Act Density 0.004%

    No Known Activations