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

    Neuronpedia

    INDEX
    Explanations

    file paths or references to directories in code

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.58
    elemField
    -0.52
    égard
    -0.51
     anaemia
    -0.50
     duquel
    -0.49
     للمعارف
    -0.49
     rzecz
    -0.48
     étoit
    -0.47
     StatelessWidget
    -0.47
     eût
    -0.47
    POSITIVE LOGITS
     "/
    2.38
     '/
    1.91
    ("/
    1.64
    ="/
    1.55
    ('/
    1.47
    "/
    1.41
    +"/
    1.35
    :'/
    1.33
     `/
    1.27
    ='/
    1.20
    Act Density 0.004%

    No Known Activations