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

    Neuronpedia

    INDEX
    Explanations

    cultural and place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ahun
    0.41
     अध्यापक
    0.40
     convincingly
    0.39
     telling
    0.39
     earnestly
    0.39
     hón
    0.38
    澼
    0.38
     ethn
    0.37
    AGUE
    0.36
    𝑦
    0.36
    POSITIVE LOGITS
     المره
    0.43
     ولا
    0.38
     Libert
    0.38
     Wol
    0.37
    ENA
    0.36
    割
    0.36
     asp
    0.35
     Extreme
    0.35
     پول
    0.35
    ésia
    0.35
    Act Density 0.010%

    No Known Activations