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

    Neuronpedia

    INDEX
    Explanations

    digits and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agreement
    0.35
     Preferably
    0.35
    🔖
    0.35
     bed
    0.34
     Miles
    0.34
     ant
    0.34
     Agreement
    0.33
    🧵
    0.33
     lime
    0.33
     ወይም
    0.32
    POSITIVE LOGITS
    compId
    0.35
    емых
    0.34
     પાસેથી
    0.32
    xFF
    0.32
    леп
    0.32
    бавить
    0.32
    月号
    0.32
     തന്റെ
    0.31
     बाप
    0.31
    ում
    0.31
    Act Density 0.021%

    No Known Activations