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

    Neuronpedia

    INDEX
    Explanations

    given provided specified

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    演
    0.40
    方面
    0.39
    充実
    0.38
    덧
    0.38
    முடைய
    0.36
    ุปกรณ์
    0.36
    <
    0.36
    갈
    0.36
    CBC
    0.34
     prévenir
    0.33
    POSITIVE LOGITS
     alcohols
    0.47
     fascism
    0.45
     bitterness
    0.45
     originality
    0.44
     ভাড়া
    0.42
     fished
    0.42
     dune
    0.42
     craftsmen
    0.42
     arriva
    0.42
    .$,
    0.41
    Act Density 0.001%

    No Known Activations