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

    Neuronpedia

    INDEX
    Explanations

    possessive or personal pronouns and related references

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

    religious phrases and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Autorisations
    -0.66
     purpoſe
    -0.62
     kasarigan
    -0.58
     Majefty
    -0.53
    GEBURTSDATUM
    -0.52
     disponibilités
    -0.52
    queryInterface
    -0.50
    TargetException
    -0.49
     myſelf
    -0.48
    utilisons
    -0.47
    POSITIVE LOGITS
     identité
    0.39
    I
    0.38
    ########.
    0.38
     âme
    0.38
    amélioration
    0.37
    null
    0.36
     للاسماء
    0.36
    __*/
    0.35
    <?
    0.35
    Now
    0.35
    Act Density 0.006%

    No Known Activations