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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associations in a structured data format

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

    Code, properties, and table definitions

    np_acts-logits-general · gemini-2.0-flash

    7

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.55
     erbjud
    -0.51
     tartalomajánló
    -0.50
    __":
    -0.50
    MethodType
    -0.50
    нрави
    -0.50
    leh
    -0.50
    AndEndTag
    -0.49
    :✨
    -0.49
    DockStyle
    -0.49
    POSITIVE LOGITS
                  
    0.97
     sixth
    0.74
     six
    0.69
     Six
    0.68
     SIX
    0.66
     intptr
    0.65
     sexto
    0.62
    Six
    0.62
     Sixth
    0.61
    Sixth
    0.61
    Act Density 0.097%

    No Known Activations