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

    Neuronpedia

    INDEX
    Explanations

    office worker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    לי
    0.44
    अपना
    0.39
    יל
    0.39
    Hasil
    0.39
    ૨
    0.39
    崠
    0.38
     DENUMIRE
    0.37
    विशेष
    0.37
    주
    0.37
    Бу
    0.37
    POSITIVE LOGITS
    0.40
     cells
    0.37
     and
    0.37
    ).
    0.36
     molecular
    0.35
     structures
    0.35
     module
    0.35
     modules
    0.35
    .
    0.34
     surface
    0.34
    Act Density 0.193%

    No Known Activations