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

    Neuronpedia

    INDEX
    Explanations

    references to societal structures and conditions, particularly those related to hierarchical systems or power dynamics

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

    special characters and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    harusnya
    -0.36
    arios
    -0.35
    anders
    -0.35
    anged
    -0.34
     zwarte
    -0.33
    ories
    -0.31
    ropractic
    -0.31
     backed
    -0.31
    ctory
    -0.31
    agic
    -0.31
    POSITIVE LOGITS
     propOrder
    0.60
     surla
    0.59
    нодоро
    0.57
    ंदीखरीदारी
    0.56
    rungsseite
    0.56
     informée
    0.55
     ویکی‌پدی
    0.53
     NSCoder
    0.53
     defaultstate
    0.52
     editText
    0.47
    Act Density 0.000%

    No Known Activations