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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or activities that involve questioning, reading, and legislative processes

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

    writing, reading, questions, lists, control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.42
    <eos>
    -0.32
    SwingConstants
    -0.27
    ↵↵↵
    -0.27
     ‘
    -0.26
     interestingly
    -0.26
     altre
    -0.26
    。
    -0.26
    Kết
    -0.25
    ().
    -0.25
    POSITIVE LOGITS
     ſta
    0.89
     myſelf
    0.87
     faſt
    0.77
     beſte
    0.77
     ſte
    0.76
     ſei
    0.75
     deſt
    0.75
     ſch
    0.75
     ſich
    0.75
     تضيفلها
    0.74
    Act Density 0.143%

    No Known Activations