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

    Neuronpedia

    INDEX
    Explanations

    clarity or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ้อน
    0.43
    torio
    0.43
    Filter
    0.39
     пробе
    0.39
    Ordering
    0.38
    티
    0.37
    ケー
    0.37
    टिंग
    0.37
     filtra
    0.37
    รา
    0.36
    POSITIVE LOGITS
     Hospitals
    0.43
     Clar
    0.43
    clar
    0.41
    Clar
    0.39
     Lucid
    0.39
     Confer
    0.38
     clarity
    0.37
     Thinking
    0.37
     Museums
    0.36
    mdb
    0.36
    Act Density 0.000%

    No Known Activations