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

    Neuronpedia

    INDEX
    Explanations

    numerical representations and data formats

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

    Numbers within lines of text

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -1.05
    исленность
    -1.03
    Rhestr
    -0.97
    Portale
    -0.96
     EconPapers
    -0.92
     SafeMath
    -0.90
    ItemBackground
    -0.87
    -0.86
    تقاوى
    -0.83
    QMetaType
    -0.82
    POSITIVE LOGITS
    3
    0.72
    4
    0.68
    5
    0.67
    1
    0.65
    2
    0.65
    7
    0.61
     
    0.61
    9
    0.60
    6
    0.60
    8
    0.55
    Act Density 2.553%

    No Known Activations