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

    Neuronpedia

    INDEX
    Explanations

    underlying explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wasnt
    0.48
     doesnt
    0.45
    পিড
    0.40
    ශ්‍ය
    0.38
     didnt
    0.37
    ዲ
    0.36
    曰
    0.36
    sparse
    0.35
    ClkInitStruct
    0.35
    hmen
    0.35
    POSITIVE LOGITS
    फे
    0.38
     headsets
    0.37
     ફે
    0.37
     graphs
    0.36
    rile
    0.36
     Saturdays
    0.36
     Afghanistan
    0.35
    icile
    0.34
     everything
    0.34
     Sicily
    0.34
    Act Density 0.001%

    No Known Activations