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

    Neuronpedia

    INDEX
    Explanations

    references to legal rules and procedures

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

    rule 56 or 59

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #
    -0.36
     Houſe
    -0.36
     Internasional
    -0.36
     ox
    -0.36
    falls
    -0.36
     bals
    -0.35
     lendemain
    -0.35
    }`).
    -0.35
     OLIVE
    -0.34
     Nusantara
    -0.34
    POSITIVE LOGITS
    rungsseite
    0.71
    hoeddwyd
    0.61
    :✨
    0.57
    styleType
    0.56
    5
    0.54
    TagMode
    0.53
     '\\;'
    0.51
    تقاوى
    0.50
     newOwner
    0.49
    ंदीखरीदारी
    0.47
    Act Density 0.098%

    No Known Activations