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

    Neuronpedia

    INDEX
    Explanations

    expressions of permission or allowances

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

    permission or authorization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cuál
    -0.55
     cuáles
    -0.50
     toiminta
    -0.49
     problemet
    -0.47
     henkil
    -0.46
     inversores
    -0.45
     rostros
    -0.44
     langkah
    -0.43
     rápidamente
    -0.42
     tuot
    -0.42
    POSITIVE LOGITS
     Allowed
    1.09
    allowed
    1.02
     allowed
    0.99
     ALLOWED
    0.94
    Allowed
    0.90
    ALLOWED
    0.87
     permitted
    0.81
    permitted
    0.80
    allowNull
    0.78
     Allowance
    0.76
    Act Density 0.011%

    No Known Activations