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

    Neuronpedia

    INDEX
    Explanations

    references to levels or aspects of various topics or subjects

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

    all aspects, directions, respects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lähteet
    -0.49
    SharedDtor
    -0.44
     some
    -0.43
    某
    -0.43
    Przypisy
    -0.41
    RenderAtEndOf
    -0.38
    ConverterFactory
    -0.38
    queryInterface
    -0.37
     RemoteException
    -0.36
     Condol
    -0.36
    POSITIVE LOGITS
     everywhere
    0.75
     Everywhere
    0.74
    Everywhere
    0.73
    everywhere
    0.72
     ovunque
    0.67
     überall
    0.66
    Everything
    0.65
     Everything
    0.61
     везде
    0.61
     partout
    0.60
    Act Density 0.020%

    No Known Activations