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

    Neuronpedia

    INDEX
    Explanations

    animal names and definitions or facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     benar
    0.34
     possible
    0.33
     iar
    0.33
     eventuali
    0.32
     menj
    0.32
     consequence
    0.31
     conseguenza
    0.31
     lain
    0.31
     penulis
    0.31
     generalized
    0.31
    POSITIVE LOGITS
    と呼ばれる
    0.35
    خدم
    0.34
    或
    0.34
    umuza
    0.33
    PMorgan
    0.33
    യാണ്
    0.33
    iculation
    0.33
     ಅಥವಾ
    0.32
    intérêt
    0.32
    Philippines
    0.32
    Act Density 0.014%

    No Known Activations