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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maine
    0.50
     executable
    0.46
     filles
    0.44
    რო
    0.44
     SIINFEKL
    0.43
    јединачна
    0.43
     adresse
    0.43
     toget
    0.42
     dam
    0.42
     collector
    0.42
    POSITIVE LOGITS
    ка
    0.45
    род
    0.44
    п
    0.43
    ни
    0.42
    он
    0.42
    氏
    0.42
    ен
    0.41
     tzw
    0.41
    ブ
    0.41
     মূলত
    0.40
    Act Density 0.002%

    No Known Activations