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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and opinions

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

    First-person perspective, often followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    for me, us

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.61
    MLLoader
    -0.60
     وتسجيلات
    -0.56
    ilerini
    -0.53
    ValueGenerated
    -0.50
    EndGlobalSection
    -0.49
    niająca
    -0.49
     μαζί
    -0.48
     you
    -0.48
     توسط
    -0.48
    POSITIVE LOGITS
     it
    1.00
    来说
    0.98
     это
    0.94
    而言
    0.92
    來說
    0.91
     isso
    0.89
     there
    0.82
     đây
    0.82
     NSCoder
    0.76
    それが
    0.73
    Act Density 0.329%

    No Known Activations