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

    Neuronpedia

    INDEX
    Explanations

    phrases related to clarity and simplicity in exposition

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

    introducing simplified explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    исленность
    -0.62
     PeEnEo
    -0.59
    Personensuche
    -0.59
    MigrationBuilder
    -0.59
     onOptions
    -0.57
    Хьажоргаш
    -0.53
    endless
    -0.52
    躇
    -0.52
    RegressionTest
    -0.51
    TagMode
    -0.50
    POSITIVE LOGITS
     convenient
    0.39
     convenience
    0.38
    方便
    0.38
     удобно
    0.36
    convenient
    0.36
     Convenient
    0.35
     propOrder
    0.33
     Convenience
    0.32
     conveniently
    0.32
    convenience
    0.32
    Act Density 0.348%

    No Known Activations