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

    Neuronpedia

    INDEX
    Explanations

    standards and compliance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.45
    :\
    0.45
     যখন
    0.45
    .\
    0.44
    \
    0.43
    =(
    0.42
     imported
    0.42
     went
    0.42
    我们需要
    0.41
     يعني
    0.40
    POSITIVE LOGITS
     fou
    0.52
     ona
    0.50
     strutture
    0.50
     participé
    0.50
     americana
    0.50
     postérieure
    0.50
     competencias
    0.50
     vati
    0.49
     artificielle
    0.49
    뢨
    0.48
    Act Density 0.003%

    No Known Activations