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

    Neuronpedia

    INDEX
    Explanations

    descriptions of polished or refined surfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    polished surfaces and professionalism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.43
     مرئيه
    -0.40
     frame
    -0.36
     situation
    -0.35
     einzu
    -0.34
     amount
    -0.34
    1
    -0.34
    illots
    -0.32
     voda
    -0.32
     весна
    -0.32
    POSITIVE LOGITS
     polishing
    1.02
    polished
    0.98
     Polished
    0.96
    polish
    0.94
     polished
    0.93
     polish
    0.90
    shiny
    0.71
    finishing
    0.67
    Shiny
    0.66
     FINISH
    0.66
    Act Density 0.002%

    No Known Activations