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

    Neuronpedia

    INDEX
    Explanations

    representation of data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ikiem
    0.41
    變成
    0.39
    ischen
    0.38
    lie
    0.38
    మారు
    0.38
    คล
    0.37
    oryt
    0.37
    Catherine
    0.37
    ด้วย
    0.37
    වත්
    0.37
    POSITIVE LOGITS
     Zulu
    0.46
     Phen
    0.43
     दैट
    0.42
     PINK
    0.42
     Sy
    0.41
     ANC
    0.41
     FUEL
    0.39
     Nova
    0.38
     AVA
    0.38
     पढ़ी
    0.38
    Act Density 0.001%

    No Known Activations