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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses like yes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    打算
    0.36
     unsuccessfully
    0.35
    kiego
    0.35
    каў
    0.34
     moindre
    0.34
    했는데
    0.34
    <unused19>
    0.33
    ícito
    0.33
    नोई
    0.33
    PrivateKey
    0.33
    POSITIVE LOGITS
     yes
    4.31
     Yes
    3.94
    Yes
    3.81
    yes
    3.78
     YES
    3.58
    YES
    3.33
     yeah
    2.77
     oui
    2.73
     yep
    2.73
     হ্যাঁ
    2.72
    Act Density 0.194%

    No Known Activations