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

    Neuronpedia

    INDEX
    Explanations

    component related code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     बच्चो
    0.59
    ียว
    0.51
     lesión
    0.49
    UI
    0.48
    植物
    0.47
    acijos
    0.47
    ビジネス
    0.47
    AH
    0.47
    وی
    0.46
    ใช่
    0.46
    POSITIVE LOGITS
     różne
    0.46
     Screening
    0.46
    captured
    0.45
    äle
    0.45
     ä
    0.45
     uncertainties
    0.45
     разные
    0.44
    декс
    0.44
     אז
    0.44
     описа
    0.43
    Act Density 0.001%

    No Known Activations