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

    Neuronpedia

    INDEX
    Explanations

    בתוך, כל, ב

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ificante
    0.94
     ಮತ್ತು
    0.91
     трябва
    0.89
     socialista
    0.88
    вЂ
    0.87
     adiab
    0.87
     anisot
    0.85
     ಅನ್ನು
    0.85
    ವನ್ನು
    0.85
    ជាមួយ
    0.84
    POSITIVE LOGITS
     những
    0.52
     ح
    0.47
     các
    0.47
     مس
    0.44
     م
    0.43
     الم
    0.42
     التع
    0.41
     الس
    0.40
     رس
    0.40
     ش
    0.40
    Act Density 0.001%

    No Known Activations