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

    Neuronpedia

    INDEX
    Explanations

    store personal information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     মুখ
    0.43
    ன
    0.43
    আনন্দ
    0.43
    寐
    0.41
    ąż
    0.40
    িতি
    0.39
    িত
    0.39
     ഭൂ
    0.39
    రుపు
    0.39
    愔
    0.38
    POSITIVE LOGITS
    unteer
    0.48
    onents
    0.47
    unteers
    0.47
     besondere
    0.46
     mirip
    0.44
     shreds
    0.43
     besonderen
    0.43
     impenetr
    0.41
     paljon
    0.41
     controvers
    0.41
    Act Density 0.012%

    No Known Activations