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

    Neuronpedia

    INDEX
    Explanations

    minor issues or suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avgsalary
    0.53
    dropBtn
    0.46
    ক্ষিত
    0.43
    謝
    0.43
    িষ্ট
    0.43
    uchsia
    0.42
    গণের
    0.42
     কপি
    0.41
    ಲಿಲ್ಲ
    0.41
    েষে
    0.41
    POSITIVE LOGITS
     pipes
    0.45
     spectra
    0.44
     Smart
    0.42
     Metabol
    0.42
     Ice
    0.41
     Cold
    0.41
     IAM
    0.40
     Spectra
    0.40
     비슷한
    0.39
     low
    0.39
    Act Density 0.000%

    No Known Activations