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

    Neuronpedia

    INDEX
    Explanations

    statements about changes or transformations in behavior or systems

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

    Tokens after punctuation (., ], ), etc.)

    np_acts-logits-general · gemini-2.0-flash

    another example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     namelijk
    -0.68
     Derfor
    -0.66
     Daarom
    -0.66
     derfor
    -0.65
    Personensuche
    -0.60
     därför
    -0.60
    Specifically
    -0.59
     namely
    -0.58
     principalement
    -0.56
     Specifically
    -0.56
    POSITIVE LOGITS
    Similarly
    1.32
     Similarly
    1.30
     another
    1.24
     Another
    1.22
    Another
    1.14
     similarly
    1.13
    another
    1.12
    Likewise
    1.12
     Likewise
    1.07
    autres
    1.04
    Act Density 0.363%

    No Known Activations