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

    Neuronpedia

    INDEX
    Explanations

    opening parentheses

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

    birth dates following names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    发表于
    -0.53
    
    -0.43
    Diweddarwch
    -0.37
    Espèce
    -0.36
     noDo
    -0.35
    enment
    -0.34
     aquello
    -0.33
    bahar
    -0.33
     debería
    -0.32
    lustre
    -0.31
    POSITIVE LOGITS
     himſelf
    0.60
     Efq
    0.58
     CURIAM
    0.57
     who
    0.57
     whom
    0.55
     مرئيه
    0.55
    랬
    0.54
    whom
    0.52
     ſei
    0.52
     tfsi
    0.52
    Act Density 0.031%

    No Known Activations