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

    Neuronpedia

    INDEX
    Explanations

    defining or describing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estaban
    0.49
     habían
    0.45
     خواهند
    0.45
     había
    0.44
     avevano
    0.44
     llegará
    0.44
     havde
    0.44
     avrà
    0.44
     avaient
    0.44
     bunları
    0.43
    POSITIVE LOGITS
     gives
    0.68
     provides
    0.63
     consists
    0.63
     helps
    0.61
     ensures
    0.60
     reduces
    0.60
     allows
    0.57
     involves
    0.56
     represents
    0.56
     enables
    0.54
    Act Density 0.035%

    No Known Activations