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

    Neuronpedia

    INDEX
    Explanations

    insurance, help, data, restrictive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     இன்னும்
    0.43
    มาชิก
    0.41
     تربیت
    0.40
    还
    0.39
     Latvij
    0.39
     অক্ষয়
    0.39
     چاندی
    0.38
     যশোরের
    0.38
     लगा
    0.38
    ምና
    0.38
    POSITIVE LOGITS
     moelle
    0.39
     Help
    0.39
     S
    0.38
    PROBLE
    0.38
     mini
    0.37
     theses
    0.37
    Adapt
    0.36
     mega
    0.36
    COMB
    0.36
     s
    0.36
    Act Density 0.003%

    No Known Activations