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

    Neuronpedia

    INDEX
    Explanations

    information about states or processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acariy
    0.50
     അദ്ദേ
    0.47
     ಅಥವಾ
    0.46
     ข้อ
    0.46
    abbanti
    0.46
     ಏಕೆ
    0.44
    Gosudarstvennyj
    0.43
    ądź
    0.43
     அல்லது
    0.43
     אם
    0.43
    POSITIVE LOGITS
     data
    0.56
    ↵
    0.55
     information
    0.54
     files
    0.50
     metadata
    0.49
     Information
    0.47
     software
    0.46
     buffer
    0.46
     Informationen
    0.46
     Data
    0.45
    Act Density 0.005%

    No Known Activations