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

    Neuronpedia

    INDEX
    Explanations

    refine and tailor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ruption
    0.64
     verursacht
    0.63
     ignor
    0.62
    চ্ছন্ন
    0.60
    ঙ্গের
    0.57
    zeti
    0.57
    vious
    0.57
    䫝
    0.57
    ယာ
    0.56
     டிக்க
    0.56
    POSITIVE LOGITS
     refine
    3.19
     refining
    3.18
     refinement
    3.15
     refined
    3.01
     refinements
    2.83
    refined
    2.48
     Refining
    2.48
     fine
    2.27
     perfecting
    1.98
    Fine
    1.93
    Act Density 1.005%

    No Known Activations