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

    Neuronpedia

    INDEX
    Explanations

    instances of legal terminology and case-related language

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

    Affirmed, House

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     op
    -0.41
     co
    -0.40
     Hofmann
    -0.35
     even
    -0.35
     these
    -0.34
     fully
    -0.33
     bad
    -0.33
     חז
    -0.32
     non
    -0.32
    ถึง
    -0.32
    POSITIVE LOGITS
     doInBackground
    0.75
     autorytatywna
    0.74
     ब्रेकडाउन
    0.69
    verifyException
    0.63
    centralwidget
    0.61
     snippetHide
    0.60
    reportWebVitals
    0.59
    Derbyniad
    0.58
    endpush
    0.58
     typelib
    0.57
    Act Density 0.001%

    No Known Activations