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

    Neuronpedia

    INDEX
    Explanations

    greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ItemsSource
    0.67
     Ouverture
    0.67
    DTDs
    0.66
     Schlacht
    0.65
     Caledonia
    0.64
     ofx
    0.63
    ffineTransform
    0.63
     প্রাদেশিক
    0.63
    ಾಪ
    0.61
     पिक्च
    0.60
    POSITIVE LOGITS
     Yash
    1.53
     Raj
    1.48
    Raj
    1.41
     Rahul
    1.41
     Ajay
    1.40
     Nikhil
    1.38
     Abhishek
    1.37
     Deepak
    1.36
     Priya
    1.36
    Neha
    1.36
    Act Density 0.212%

    No Known Activations