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

    Neuronpedia

    INDEX
    Explanations

    `strftime` formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ज
    2.00
    uk
    1.81
    可以
    1.69
    נה
    1.58
    М
    1.52
    จะ
    1.51
    ور
    1.49
    возмо
    1.46
    л
    1.45
    와
    1.45
    POSITIVE LOGITS
    ductory
    2.19
    ا
    2.11
    theless
    1.85
    ্লাহ
    1.85
    shire
    1.71
    dür
    1.70
    یی
    1.69
    вання
    1.66
    יות
    1.66
    ment
    1.64
    Act Density 0.067%

    No Known Activations