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

    Neuronpedia

    INDEX
    Explanations

    words related to knowledge and understanding

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

    Followed by "know" or a synonym

    np_acts-logits-general · gemini-2.0-flash

    knowing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kháu
    -0.76
    显得
    -0.49
    üman
    -0.48
     Ideas
    -0.47
    zkod
    -0.46
     Erwä
    -0.46
    tagHelperRunner
    -0.45
    newtheorem
    -0.45
    instead
    -0.45
     istället
    -0.44
    POSITIVE LOGITS
     intimately
    1.03
     firsthand
    0.85
     Bescheid
    0.82
     well
    0.81
     better
    0.78
     intuitively
    0.75
     جيد
    0.72
    enough
    0.70
     enough
    0.69
    Personendaten
    0.69
    Act Density 0.242%

    No Known Activations