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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal terminology and procedural language

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

    then, others, improve, where, while

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    URLException
    -0.38
     nakalista
    -0.37
     wanna
    -0.37
    出版年
    -0.37
     outta
    -0.36
     gotta
    -0.35
    Permalink
    -0.34
     weird
    -0.34
    urlpatterns
    -0.34
    ViewImports
    -0.34
    POSITIVE LOGITS
    хьтан
    0.66
    IVEREF
    0.61
     således
    0.59
    msgTypes
    0.57
     pertanto
    0.57
     esternos
    0.54
     transfieras
    0.54
    较为
    0.54
    postsleuth
    0.53
     endast
    0.53
    Act Density 0.268%

    No Known Activations