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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreement, consistency, or alignment between concepts

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

    aligned with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.61
     estekak
    -0.55
     الحره
    -0.54
    ftagPool
    -0.53
     compar
    -0.52
     صوتيه
    -0.51
     otomatig
    -0.49
     للاسماء
    -0.48
    -0.48
    RuleContext
    -0.47
    POSITIVE LOGITS
    rouvez
    0.45
     Consultez
    0.37
     Vorstellung
    0.37
    符合
    0.35
    tième
    0.35
     Nad
    0.35
    -------
    0.34
    ="/">
    0.34
     entspricht
    0.34
     Consulte
    0.33
    Act Density 0.090%

    No Known Activations