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

    Neuronpedia

    INDEX
    Explanations

    proof and evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    neutrophiles
    0.50
    dayspecial
    0.49
    TempValue
    0.47
     جرام
    0.46
    塢
    0.46
    numberOfRecords
    0.46
     হলো
    0.45
     кушымта
    0.45
     말미암
    0.45
    imageCache
    0.44
    POSITIVE LOGITS
    证明
    1.19
     chứng
    1.16
     prove
    1.14
     Chứng
    1.14
     доказа
    1.08
     Prove
    1.07
    Chứng
    1.07
    證明
    1.05
    Prove
    1.03
     증
    1.02
    Act Density 0.000%

    No Known Activations