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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming, including function definitions and structured data formats

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

    Code snippets with bracket-like characters and numbers

    np_acts-logits-general · gemini-2.0-flash

    strings in quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !")
    -1.00
    存于互联网档案馆
    -0.95
    abestanden
    -0.94
    "):
    -0.94
     ſind
    -0.90
     ་་
    -0.90
     photolibrary
    -0.88
    .")
    -0.87
    __":
    -0.87
     الحره
    -0.85
    POSITIVE LOGITS
     
    1.05
    1
    0.90
    0
    0.81
     A
    0.79
     B
    0.78
     "
    0.77
    :
    0.77
    B
    0.76
    _
    0.76
    2
    0.74
    Act Density 2.067%

    No Known Activations