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

    Neuronpedia

    INDEX
    Explanations

    word or phrase completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     መሳሪያ
    0.28
    雱
    0.26
     للد
    0.26
     навча
    0.26
     dün
    0.26
     gemüt
    0.26
     Marian
    0.25
     প
    0.25
     građ
    0.25
     의료
    0.25
    POSITIVE LOGITS
    하게
    0.38
    ly
    0.36
     by
    0.35
     edilir
    0.35
    になる
    0.32
    ately
    0.31
     गर्ने
    0.31
    in
    0.31
    になり
    0.31
    by
    0.30
    Act Density 0.059%

    No Known Activations