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

    Neuronpedia

    INDEX
    Explanations

    patterns of numbers and symbols, likely those related to monetary values or statistics

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

    Non-English words or code snippets

    np_acts-logits-general · gemini-2.0-flash

    living room

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.86
    InvalidProtocol
    -0.70
     iNdEx
    -0.67
    adaptiveStyles
    -0.66
    ]--;
    -0.63
    StoryboardSegue
    -0.62
    Karakteristik
    -0.62
     ligiloj
    -0.62
    Personensuche
    -0.60
    \}\\
    -0.60
    POSITIVE LOGITS
     malheure
    0.53
    ومن
    0.52
     étoit
    0.52
    هذا
    0.50
     băr
    0.50
     ansik
    0.49
     fotografico
    0.49
     كما
    0.48
     giustizia
    0.47
    makeConstraints
    0.47
    Act Density 0.007%

    No Known Activations