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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating awareness and communication

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

    exception, errors, code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ne
    -0.31
     coupling
    -0.31
     SEÑ
    -0.30
    coupling
    -0.30
    nt
    -0.30
     מוכ
    -0.30
    nexo
    -0.30
     Klo
    -0.29
    Enllaces
    -0.29
     OFDb
    -0.28
    POSITIVE LOGITS
    MethodManager
    0.71
     queſta
    0.63
     témoig
    0.57
    yntaxException
    0.55
    تقاوى
    0.54
    rungsseite
    0.53
    meteries
    0.50
     laſſen
    0.50
    +#+#
    0.50
    encodeWith
    0.50
    Act Density 0.093%

    No Known Activations