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

    Neuronpedia

    INDEX
    Explanations

    terms related to equality and inclusivity

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

    not all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithMany
    -0.36
     تانيه
    -0.35
    انجليز
    -0.35
    bodyParser
    -0.34
    Билгалдахарш
    -0.34
    DateTimeField
    -0.32
    GeneratedValue
    -0.31
    CharStream
    -0.31
    mostly
    -0.30
     plupart
    -0.30
    POSITIVE LOGITS
    msgTypes
    0.70
    0.56
    хьтан
    0.55
     createState
    0.53
    存于互联网档案馆
    0.50
    ViewInit
    0.50
    ilirsiniz
    0.49
    └──
    0.47
     noDo
    0.47
    featureID
    0.47
    Act Density 0.008%

    No Known Activations