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

    Neuronpedia

    INDEX
    Explanations

    point index stock force

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Không
    0.49
    人々
    0.47
    Лю
    0.47
    re
    0.46
    Let
    0.45
    Sector
    0.45
    ice
    0.44
    they
    0.44
    joining
    0.44
    Barcelona
    0.44
    POSITIVE LOGITS
    leqslant
    0.43
     সংস
    0.42
     посо
    0.42
    roidism
    0.42
     ASH
    0.42
     cooldown
    0.42
     қай
    0.42
    пе
    0.41
    лят
    0.41
     tweezers
    0.41
    Act Density 0.015%

    No Known Activations