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

    Neuronpedia

    INDEX
    Explanations

    references to political parties and their principles, particularly regarding fiscal responsibility and religious beliefs

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

    political and social concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.71
     שוליים
    -0.60
     CreateTagHelper
    -0.56
     '\\;'
    -0.54
     հղումներ
    -0.49
     tartalomajánló
    -0.49
    DockStyle
    -0.49
    Général
    -0.48
    __':
    -0.48
     препратки
    -0.48
    POSITIVE LOGITS
     itſelf
    0.58
     supposed
    0.48
    FunctionFlags
    0.45
     poffible
    0.45
     leſs
    0.43
     fhould
    0.42
     fhew
    0.41
     themſelves
    0.40
     uſ
    0.40
     ſta
    0.39
    Act Density 0.064%

    No Known Activations