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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document

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

    Opening tags or XML-like structures

    np_acts-logits-general · gemini-2.0-flash

    stages HH18

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -1.07
     (
    -0.99
     and
    -0.97
     a
    -0.95
     in
    -0.94
     for
    -0.92
     all
    -0.91
    ,
    -0.91
     “
    -0.90
     or
    -0.87
    POSITIVE LOGITS
     ་་
    1.57
    NUMX
    1.34
     myſelf
    1.33
     ―――――
    1.33
    ſelves
    1.32
     itſelf
    1.31
     iſt
    1.31
     Efq
    1.29
    存于互联网档案馆
    1.27
     ſind
    1.24
    Act Density 0.147%

    No Known Activations