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

    Neuronpedia

    INDEX
    Explanations

    instances of stream insertion operators in code output

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

    endl with std::cout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cyfeiriadau
    -0.43
     Савезне
    -0.42
    MathML
    -0.41
     Lipa
    -0.41
    hyrchwyd
    -0.41
     Farm
    -0.41
    asteroide
    -0.40
     RMA
    -0.40
     def
    -0.39
     either
    -0.39
    POSITIVE LOGITS
    makeConstraints
    0.66
    󠁴
    0.61
    ()<<
    0.57
    retudo
    0.54
    )<<
    0.54
    ]<<
    0.52
     miniaturka
    0.52
     <<
    0.52
     numberWith
    0.52
     ainfi
    0.52
    Act Density 0.006%

    No Known Activations