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

    Neuronpedia

    INDEX
    Explanations

    without warranty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thisStudent
    0.41
    ழுகு
    0.40
    निम्नलिखित
    0.38
    Khokhlov
    0.38
     vinaig
    0.38
     spirals
    0.38
     unbalanced
    0.38
     změ
    0.37
     pétales
    0.37
    শুধ
    0.37
    POSITIVE LOGITS
     warranties
    1.23
     warranty
    1.19
    warranty
    1.11
    Warranty
    1.08
     Warranty
    1.06
     WARRANTY
    0.91
     garantías
    0.87
     garantie
    0.86
     guarantees
    0.86
     гаран
    0.85
    Act Density 0.003%

    No Known Activations