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

    Neuronpedia

    INDEX
    Explanations

    list structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ociaż
    0.45
     různých
    0.44
     berbagai
    0.43
     olika
    0.43
     Bogdan
    0.42
     صدای
    0.41
     diversos
    0.41
     assorted
    0.41
     Beograd
    0.40
     বিভিন্ন
    0.40
    POSITIVE LOGITS
     प्राइमरी
    0.40
     preoperative
    0.40
    opropane
    0.37
     ~(
    0.37
    Groups
    0.37
     ADMINISTRATIVE
    0.36
     subsistence
    0.35
    ADEL
    0.35
     собственно
    0.35
    Quantitative
    0.35
    Act Density 0.274%

    No Known Activations