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

    Neuronpedia

    INDEX
    Explanations

    structured text and code markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gå
    0.35
     πάνω
    0.35
    ग्राहक
    0.35
     पाउडर
    0.34
    Jeśli
    0.33
    okolade
    0.33
    欢
    0.33
    䀨
    0.32
    สัตว์
    0.32
     अल्कोहल
    0.32
    POSITIVE LOGITS
    ↵
    0.41
     b
    0.33
     An
    0.32
     non
    0.31
     laptop
    0.30
    ↵↵
    0.30
     Laptop
    0.29
     Assumption
    0.29
     P
    0.29
     H
    0.29
    Act Density 0.021%

    No Known Activations