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

    Neuronpedia

    INDEX
    Explanations

    expressions of sentiment and emotional states

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

    first or beginning words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.56
     MaterialApp
    -0.46
    #+#
    -0.45
     Fintech
    -0.44
     hvid
    -0.42
     prêtres
    -0.41
    MemoryWarning
    -0.41
     HttpHeaders
    -0.40
    ⓧ
    -0.40
     endblock
    -0.40
    POSITIVE LOGITS
    ส่วน
    1.91
     ส่วน
    1.35
    随
    0.62
     bagian
    0.59
     Bagian
    0.56
     bản
    0.55
    tend
    0.51
    tvguidetime
    0.50
    隨
    0.50
     Bản
    0.49
    Act Density 0.001%

    No Known Activations