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

    Neuronpedia

    INDEX
    Explanations

    lists and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tych
    0.30
     itibaren
    0.30
    ंडीज
    0.30
     haunts
    0.29
     `.
    0.29
     isang
    0.29
     `${
    0.28
    :`
    0.28
     হানাদার
    0.28
    ൫
    0.28
    POSITIVE LOGITS
    administrative
    0.31
    romechanical
    0.31
     끊
    0.31
    RPG
    0.30
     힘
    0.29
    administrat
    0.29
    STEM
    0.29
    mechanical
    0.29
    skilled
    0.29
     médic
    0.29
    Act Density 0.013%

    No Known Activations