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

    Neuronpedia

    INDEX
    Explanations

    instances of examples or case studies being presented

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

    preceding "example" or "examples"

    np_acts-logits-general · gemini-2.0-flash

    example or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jspb
    -0.70
     ComVisible
    -0.67
    出版年
    -0.64
     GenerationType
    -0.62
     Efq
    -0.62
    StoryboardSegue
    -0.59
    MessageOf
    -0.59
    AutoField
    -0.57
    sizeCache
    -0.56
    úsqueda
    -0.56
    POSITIVE LOGITS
     example
    3.16
     examples
    3.04
    example
    2.62
    Example
    2.52
     Example
    2.51
     Examples
    2.47
    examples
    2.46
    Examples
    2.42
     ejemplo
    2.41
     contoh
    2.36
    Act Density 0.930%

    No Known Activations