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

    Neuronpedia

    INDEX
    Explanations

    basic functionality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अनुप
    0.45
    юра
    0.45
     شپ
    0.44
     constable
    0.44
     EUROPE
    0.43
     дизайнер
    0.42
    ropshire
    0.41
     للمعارف
    0.41
     british
    0.40
    欧盟
    0.40
    POSITIVE LOGITS
     unjust
    0.44
     malnourished
    0.39
     butt
    0.37
     zach
    0.37
     interaction
    0.37
     retarded
    0.36
    ereg
    0.36
    せい
    0.36
     Здравствуйте
    0.36
    asc
    0.35
    Act Density 0.000%

    No Known Activations