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

    Neuronpedia

    INDEX
    Explanations

    legal terminology related to due process and judicial analysis

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

    "Is" or words indicating importance

    np_acts-logits-general · gemini-2.0-flash

    is significant that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.87
     فريبيس
    -0.85
    writeFieldEnd
    -0.84
     BoxDecoration
    -0.80
     ComVisible
    -0.77
     GenerationType
    -0.74
    principalTable
    -0.74
    PreferredItem
    -0.74
    wpi
    -0.73
     متعلقه
    -0.72
    POSITIVE LOGITS
     perhaps
    0.68
    perhaps
    0.62
    Perhaps
    0.56
     assai
    0.54
     crucial
    0.54
     here
    0.53
     somewhat
    0.53
     Perhaps
    0.52
     kritik
    0.51
     illuminating
    0.50
    Act Density 1.029%

    No Known Activations