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

    Neuronpedia

    INDEX
    Explanations

    upfront quotes and estimates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بين
    0.48
    ຢູ່
    0.46
     कुठे
    0.46
     ആരാധ
    0.45
     между
    0.45
     ዓይነ
    0.45
    ัก
    0.43
    专属
    0.43
    żyt
    0.43
     څ
    0.43
    POSITIVE LOGITS
     was
    0.50
    ,
    0.46
     is
    0.46
     tons
    0.45
     that
    0.43
     atmosphere
    0.43
     seems
    0.43
     (
    0.43
     kefir
    0.43
                  
    0.42
    Act Density 0.001%

    No Known Activations