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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation associated with protective measures or constraints in formal contexts

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

    protect against opponent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.51
     ſch
    -0.49
     anhänger
    -0.44
     dieß
    -0.41
     exercí
    -0.39
     nocy
    -0.39
     stanga
    -0.39
     miniaturka
    -0.38
     rigue
    -0.38
     leſs
    -0.35
    POSITIVE LOGITS
     للمعارف
    0.73
    MLLoader
    0.71
    yarnpkg
    0.67
     <<<<<<<<<<<<<<
    0.66
     '{@
    0.60
    出版年
    0.59
    AddTagHelper
    0.59
     שוליים
    0.58
     تانيه
    0.58
    !*\
    0.57
    Act Density 0.080%

    No Known Activations