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

    Neuronpedia

    INDEX
    Explanations

    references to being new or a beginner in various contexts

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

    new to something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.66
    awtextra
    -0.56
    Бахар
    -0.54
    ngdoc
    -0.50
     оригіналу
    -0.50
    hyrchwyd
    -0.49
    RectangleBorder
    -0.49
     <<<<<<<<<<<<<<
    -0.48
    Datuak
    -0.48
     الحره
    -0.48
    POSITIVE LOGITS
     cyn
    0.40
     VC
    0.40
     впервые
    0.39
     dealing
    0.38
     ند
    0.37
    boutin
    0.36
     dum
    0.36
    VC
    0.36
     Delf
    0.35
    κτη
    0.35
    Act Density 0.026%

    No Known Activations