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

    Neuronpedia

    INDEX
    Explanations

    references to events or actions that are organized or produced for display or performance

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

    preparing or classifying stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     compañ
    -0.47
     advisers
    -0.46
     المعيارى
    -0.45
     mention
    -0.44
     advis
    -0.43
     adviser
    -0.43
     sabiduría
    -0.41
    مصادر
    -0.40
     friends
    -0.40
     advisors
    -0.39
    POSITIVE LOGITS
     staged
    1.56
     Staging
    1.23
     staging
    1.18
    Staging
    1.10
    staging
    0.96
     Stage
    0.83
    Stage
    0.76
     STAGE
    0.75
    stage
    0.69
     stage
    0.68
    Act Density 0.005%

    No Known Activations