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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating realization or understanding of important information

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

    clear, known, or learned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prefixer
    -0.30
    ibase
    -0.30
    melin
    -0.30
    denas
    -0.28
     Bedürfn
    -0.28
    prefs
    -0.28
     Erfolgs
    -0.28
    Stopping
    -0.27
    ADD
    -0.26
    Growth
    -0.26
    POSITIVE LOGITS
    出版年
    0.65
    帖最后由
    0.63
     insuffisamment
    0.61
     ujednoznacz
    0.60
    OGND
    0.60
    Билгалдахарш
    0.58
    localctx
    0.58
     насељу
    0.57
     OMITBAD
    0.57
    хьтан
    0.56
    Act Density 0.217%

    No Known Activations