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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and concepts related to rights and agreements

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

    Preceding words: "by", "He", "I", "She", "you"

    np_acts-logits-general · gemini-2.0-flash

    teaching and explaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SafeArea
    -0.43
    Received
    -0.43
    Reporter
    -0.42
    multirow
    -0.42
     osta
    -0.41
     salto
    -0.41
    Dreaming
    -0.41
     Ranked
    -0.40
    سة
    -0.39
    IComponent
    -0.39
    POSITIVE LOGITS
     explain
    1.60
     explaining
    1.59
     teach
    1.47
     explained
    1.44
     Explain
    1.41
     teaching
    1.38
    Explain
    1.31
    explain
    1.30
    Remind
    1.25
     Remind
    1.24
    Act Density 0.608%

    No Known Activations