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

    Neuronpedia

    INDEX
    Explanations

    private helper functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setpos
    0.38
    larında
    0.37
     plans
    0.36
    ndon
    0.35
     प्लान
    0.35
    larına
    0.35
     circunstancias
    0.35
    لاف
    0.35
    लग
    0.35
     نتی
    0.35
    POSITIVE LOGITS
    Helper
    0.54
     helper
    0.52
     Helper
    0.52
    helper
    0.51
    辅助
    0.50
    PRIVATE
    0.48
    輔
    0.46
     utility
    0.45
     सहायक
    0.44
     helpful
    0.44
    Act Density 0.009%

    No Known Activations