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

    Neuronpedia

    INDEX
    Explanations

    areas, gaps, absence, first, files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     antioxid
    0.44
     liberdade
    0.44
     photographie
    0.44
     mel
    0.42
     anticoag
    0.40
    度的
    0.39
     Ekiti
    0.39
     melatonin
    0.39
    सादर
    0.39
     ps
    0.38
    POSITIVE LOGITS
    슴
    0.40
     legacy
    0.37
     Legacy
    0.36
     Solve
    0.36
     주제
    0.36
    극
    0.34
    主题
    0.34
    OK
    0.34
    辘
    0.34
    椥
    0.33
    Act Density 0.000%

    No Known Activations