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

    Neuronpedia

    INDEX
    Explanations

    foreign language text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GAAP
    0.47
    డ్డి
    0.45
     Merino
    0.44
     erred
    0.43
     DVDs
    0.43
    蓣
    0.43
     (
    0.43
     Bit
    0.43
     Brick
    0.42
    tte
    0.42
    POSITIVE LOGITS
    在
    0.51
    тель
    0.50
    ین
    0.50
    ва
    0.47
    ید
    0.46
    는
    0.45
    き
    0.45
    чні
    0.45
     in
    0.45
    த்தில்
    0.44
    Act Density 0.168%

    No Known Activations