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

    Neuronpedia

    INDEX
    Explanations

    verb-noun pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PRES
    0.48
     mathematical
    0.48
    㙂
    0.47
     SCIENCE
    0.47
     adimensional
    0.47
    хан
    0.46
     नीचे
    0.45
     નીચે
    0.45
     défendre
    0.44
     solução
    0.44
    POSITIVE LOGITS
    ؛
    0.45
    ains
    0.44
    urados
    0.44
     voisins
    0.44
    fois
    0.42
     battles
    0.42
    ıyor
    0.41
    né
    0.41
    뿐
    0.41
     effectuées
    0.40
    Act Density 0.000%

    No Known Activations