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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and variables commonly used in equations

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

    Mathematical or probability equations/symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.49
     ​​
    -0.48
     even
    -0.46
    Так
    -0.45
    fxml
    -0.44
    ADVERTISEMENT
    -0.43
    …
    -0.42
     PartialEq
    -0.41
     "
    -0.40
     par
    -0.40
    POSITIVE LOGITS
     Efq
    0.88
     ExecuteAsync
    0.88
     fevere
    0.87
     avoient
    0.86
     auroit
    0.85
     Majefty
    0.84
     houſe
    0.83
     purpoſe
    0.83
     moschino
    0.83
     reaſon
    0.83
    Act Density 2.470%

    No Known Activations