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

    Neuronpedia

    INDEX
    Explanations

    pronouns and definite articles in various contexts

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

    theatrical employees or assisted reproductive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ро
    -0.21
    File
    -0.20
     Stadt
    -0.19
    e
    -0.19
     мо
    -0.18
     suel
    -0.17
    ตัว
    -0.17
    II
    -0.17
    DataManager
    -0.17
    身
    -0.17
    POSITIVE LOGITS
    脚注の使い方
    1.12
    <unused74>
    1.05
    ſammen
    1.05
    [@BOS@]
    1.05
    <unused41>
    1.05
    <unused16>
    1.05
    <unused28>
    1.05
    <unused14>
    1.05
    <unused3>
    1.05
    <unused8>
    1.05
    Act Density 0.312%

    No Known Activations