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

    Neuronpedia

    INDEX
    Explanations

    intentionally misspelled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    지의
    0.44
    blk
    0.43
     Treatment
    0.42
    量的
    0.40
     coupled
    0.40
    тивные
    0.40
    .),
    0.40
    icznej
    0.40
    치의
    0.40
    Np
    0.39
    POSITIVE LOGITS
    蕎
    0.47
     iccad
    0.47
    すご
    0.46
     विनो
    0.46
     gând
    0.44
     особа
    0.43
    መሳ
    0.43
     bå
    0.42
     parr
    0.42
     modele
    0.41
    Act Density 0.004%

    No Known Activations