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

    Neuronpedia

    INDEX
    Explanations

    unlimited / number of choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sangat
    0.45
     poiché
    0.44
     fractions
    0.41
     bardzo
    0.41
     vrlo
    0.40
    Variants
    0.39
     Nan
    0.39
     Variations
    0.39
     labai
    0.38
     joyas
    0.38
    POSITIVE LOGITS
    棲
    0.41
     pessoal
    0.41
     персонал
    0.39
    Residence
    0.39
    carte
    0.39
    個人
    0.39
    رے
    0.38
    個人的
    0.38
    Personally
    0.38
    personal
    0.37
    Act Density 0.000%

    No Known Activations