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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and computations

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

    mathematical expressions with exponents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Differenz
    -0.39
     Unterschiede
    -0.37
     communs
    -0.37
     difference
    -0.36
    mits
    -0.35
    området
    -0.35
     Beobachtung
    -0.35
     Empfindung
    -0.34
    vaadin
    -0.34
    okovic
    -0.34
    POSITIVE LOGITS
    :✨
    0.69
     Савезне
    0.62
    InitVars
    0.59
     ویکی‌پدی
    0.58
    principalColumn
    0.56
    RegressionTest
    0.51
     SqlParameter
    0.47
    GOTREF
    0.46
    PyTuple
    0.46
    minecraftforge
    0.45
    Act Density 0.269%

    No Known Activations