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

    Neuronpedia

    INDEX
    Explanations

    taking a deep breath

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अदालत
    0.43
     Michel
    0.40
     ngôi
    0.37
     Saturday
    0.37
     printers
    0.37
     millioner
    0.37
    cienza
    0.37
    Countryside
    0.37
     শনিবার
    0.37
     minutes
    0.36
    POSITIVE LOGITS
    which
    0.45
    म्प्ट
    0.42
     கவர்
    0.42
     مِنْ
    0.41
    গেট
    0.41
     ác
    0.40
    qe
    0.40
    吘
    0.40
     quae
    0.40
     डिप्ट
    0.38
    Act Density 0.001%

    No Known Activations