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

    Neuronpedia

    INDEX
    Explanations

    international phrases and topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    爯
    0.38
     appunto
    0.36
     selaku
    0.33
     désir
    0.32
    ്യാ
    0.31
    ি
    0.31
    一方面
    0.31
    ބ
    0.30
     vật
    0.30
    ceğ
    0.29
    POSITIVE LOGITS
     Австра
    0.38
     Include
    0.37
     высокого
    0.37
     включая
    0.37
     include
    0.36
    大全
    0.35
     краса
    0.34
    დან
    0.34
     включает
    0.33
     британ
    0.33
    Act Density 0.142%

    No Known Activations