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

    Neuronpedia

    INDEX
    Explanations

    references to high-quality or satisfactory outcomes and performance attributes

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

    satisfactory, ie

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enoord
    -0.39
     mû
    -0.35
    ิลปะ
    -0.34
     docteur
    -0.34
     太郎
    -0.34
    PreferredItem
    -0.33
     empuj
    -0.33
    MÁS
    -0.33
     fubject
    -0.33
    userRepository
    -0.32
    POSITIVE LOGITS
    
    0.57
    istoitu
    0.57
     AssemblyTitle
    0.54
     transfieras
    0.54
    Datuak
    0.47
     ModelExpression
    0.46
    rrggbb
    0.46
    ✨:
    0.45
    Rüyada
    0.45
     Zebra
    0.45
    Act Density 0.005%

    No Known Activations