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

    Neuronpedia

    INDEX
    Explanations

    specific names and references related to movies, products, and brands

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

    product names or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     internetowa
    -0.39
     zupeł
    -0.36
     Hauptstadt
    -0.35
     Küste
    -0.35
    fromnode
    -0.34
     sabias
    -0.34
     Kreise
    -0.33
     preocupação
    -0.33
     Grundlage
    -0.33
     Gästen
    -0.33
    POSITIVE LOGITS
    rafts
    0.58
    PyExc
    0.56
    Pyx
    0.56
     lenker
    0.55
    neuri
    0.54
     CFL
    0.54
     CDI
    0.54
    orch
    0.54
     Illumin
    0.53
    Framed
    0.52
    Act Density 0.040%

    No Known Activations